{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":52,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":52,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"34b188fc4f0f","filters":{"venue":"Transactions of the Association for Computational Linguistics"}},"results":[{"id":"W2911227954","doi":"10.1162/tacl_a_00041","title":"Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":808,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Macquarie University; York University; University of Washington; University of California, San Diego; National Science Foundation","keywords":"Embarrassment; Computer science; Natural (archaeology); Data science; Field (mathematics); Natural language; Lead (geology); Style (visual arts); Engineering ethics; Natural language processing; Psychology; Social psychology","authors":[{"name":"Emily M. Bender","is_ca":false},{"name":"Batya Friedman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06724238139102369,"gpt":0.3486267136322955,"spread":0.2813843322412718,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001040362,0.00008277925,0.0001154561,0.00008800314,0.0006307623,0.0001744528,0.0007515508,0.00003308117,2.752853e-7],"category_scores_gemma":[0.001464541,0.00007252009,0.00004040891,0.0002829642,0.00008156747,0.0002633239,0.00007212115,0.00007421917,4.418186e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001918678,"about_ca_system_score_gemma":0.0002303411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001639019,"about_ca_topic_score_gemma":0.000007367029,"domain_scores_codex":[0.9987336,0.00002583263,0.0003345165,0.000294184,0.0004242021,0.0001876903],"domain_scores_gemma":[0.9974296,0.000449778,0.0003731175,0.0002653386,0.001449169,0.00003297594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001752122,0.0006254512,0.0116395,0.00499913,0.001014867,0.000001681007,0.04147508,0.2156678,0.003127392,0.3679345,0.001178781,0.3521606],"study_design_scores_gemma":[0.0004052899,0.00002500848,0.0003626827,0.00006722376,0.00003556088,9.827248e-7,0.000241395,0.9950996,0.0006652265,0.002375625,0.0006384904,0.00008293195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006648411,0.00005461713,0.9911957,0.0003660802,0.001049417,0.0003257825,0.000217587,0.00005824554,0.00008412446],"genre_scores_gemma":[0.6946006,2.516228e-7,0.3050706,0.00005648428,0.0001901187,0.000008881297,0.00001818428,0.000005469771,0.00004937191],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7794318,"threshold_uncertainty_score":0.4851377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3151929433","doi":"10.1162/tacl_a_00360","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":602,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; HEC Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Kepler; Embedding; Benchmark (surveying); Language model; Representation (politics); Natural language processing; Construct (python library); ENCODE; Artificial intelligence; Programming language","authors":[{"name":"Xiaozhi Wang","is_ca":false},{"name":"Tianyu Gao","is_ca":false},{"name":"Zhaocheng Zhu","is_ca":true},{"name":"Zhengyan Zhang","is_ca":false},{"name":"Zhiyuan Liu","is_ca":false},{"name":"Juanzi Li","is_ca":false},{"name":"Jian Tang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03147363115435537,"gpt":0.3240863137469095,"spread":0.2926126825925541,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002917282,0.00008029443,0.0001368116,0.00005438758,0.0002470258,0.0000615193,0.0001958445,0.00006295403,9.218451e-7],"category_scores_gemma":[0.001681528,0.00008080307,0.0001244867,0.0002018253,0.00001426938,0.00006531322,0.00002143575,0.00007029317,2.703899e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056683,"about_ca_system_score_gemma":0.0002082442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007195771,"about_ca_topic_score_gemma":0.00002280106,"domain_scores_codex":[0.999116,0.00004474204,0.0002995125,0.0002196717,0.000193905,0.000126147],"domain_scores_gemma":[0.9973218,0.001111844,0.0002167669,0.0001934551,0.001125724,0.0000303466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008329846,0.00005420297,0.00008059449,0.00005025341,0.00005542739,6.754033e-8,0.002822822,0.897187,0.0001539181,0.09796598,0.00007959981,0.001541781],"study_design_scores_gemma":[0.0005669486,0.00001346673,0.0002882071,0.00001800716,0.00005112718,0.000001026585,0.00009356833,0.9495437,0.0005865793,0.04854103,0.000218591,0.00007772139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00263066,0.0000544465,0.9956169,0.0004446331,0.0004955236,0.0003085322,0.0001145145,0.00005237757,0.0002824734],"genre_scores_gemma":[0.6736804,0.000002287419,0.3246725,0.00003791565,0.00007545188,0.0000279314,0.00002745661,0.000007230752,0.00146884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6710497,"threshold_uncertainty_score":0.3295054,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906152891","doi":"10.1162/tacl_a_00254","title":"Analysis Methods in Neural Language Processing: A Survey","year":2019,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":486,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Categorization; Artificial neural network; Field (mathematics); Feature (linguistics); Artificial intelligence; Point (geometry); Data science; Natural language processing; Machine learning; Linguistics","authors":[{"name":"Yonatan Belinkov","is_ca":true},{"name":"James Glass","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02963772496761502,"gpt":0.3494461539490562,"spread":0.3198084289814412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001091843,0.00007097794,0.0001853252,0.0001825871,0.00007094433,0.00004294249,0.0003973121,0.00005388455,0.000004144826],"category_scores_gemma":[0.0009145654,0.00006449757,0.0001572793,0.001030679,0.000008384871,0.00005422533,0.00001513268,0.0001088349,0.000001416203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000135034,"about_ca_system_score_gemma":0.0001028493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001326668,"about_ca_topic_score_gemma":0.0001184361,"domain_scores_codex":[0.9989086,0.0001844503,0.0003341014,0.0001806312,0.0002669396,0.0001252994],"domain_scores_gemma":[0.9978198,0.001099121,0.0002801667,0.0002058112,0.0005759592,0.00001911823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000421122,0.00004150048,0.04908028,0.00001608811,0.00007863343,3.966525e-8,0.0004784254,0.9440999,0.00001075115,0.002546921,0.000004128119,0.003639092],"study_design_scores_gemma":[0.0002306883,0.00001078579,0.095353,0.000005102137,0.00005575076,1.212935e-7,0.00001937323,0.9023499,0.00004010436,0.001797109,0.00007609629,0.00006194824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00855588,0.00003770179,0.9902783,0.0001318183,0.0004768416,0.0001933581,0.00004133898,0.00002921039,0.0002555696],"genre_scores_gemma":[0.7810395,2.652203e-7,0.2185252,0.00003731237,0.00002048184,0.000006312727,0.0000141941,0.000004230401,0.0003524809],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7724836,"threshold_uncertainty_score":0.2630135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2531207078","doi":"10.1162/tacl_a_00067","title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":415,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University; Samsung Advanced Institute of Technology; Samsung; Nvidia","keywords":"Computer science; Machine translation; Character (mathematics); Pooling; Encoder; Convolutional neural network; Artificial intelligence; Translation (biology); Natural language processing; Segmentation; Speech recognition; Task (project management); Language model; Representation (politics)","authors":[{"name":"Jason D. Lee","is_ca":false},{"name":"Kyunghyun Cho","is_ca":false},{"name":"Thomas Hofmann","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0388812594394734,"gpt":0.3152326302466266,"spread":0.2763513708071532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003798039,0.0001332793,0.0001696082,0.00008567418,0.0008613162,0.0002327641,0.0008889502,0.00009183127,0.000003070911],"category_scores_gemma":[0.0007420413,0.0001172917,0.0001633846,0.0001143636,0.0000315823,0.0002992472,0.00002469526,0.000164508,0.000001709637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001537786,"about_ca_system_score_gemma":0.00008464771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000481871,"about_ca_topic_score_gemma":0.00002834939,"domain_scores_codex":[0.9987463,0.00005020835,0.0003708081,0.0002148792,0.0004579178,0.0001599182],"domain_scores_gemma":[0.997462,0.0003114766,0.0008655998,0.0003826049,0.0009440435,0.00003427954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003536101,0.0011929,0.03445466,0.000664079,0.0009492958,0.000002528283,0.005456393,0.1344965,0.008753503,0.4301081,0.0009444132,0.3826241],"study_design_scores_gemma":[0.001111703,0.00008624076,0.01301074,0.00005492312,0.0001120921,0.000003446885,0.00001172158,0.9091198,0.007931241,0.06725673,0.001023117,0.0002782338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007539887,0.00009202367,0.9957358,0.001437056,0.001019021,0.0004084456,0.0002174468,0.0001360117,0.0002001537],"genre_scores_gemma":[0.664817,0.000002060736,0.3346779,0.0000673311,0.000100672,0.00002390619,0.0000346947,0.000009692662,0.0002666587],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7746233,"threshold_uncertainty_score":0.6624635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3207937903","doi":"10.1162/tacl_a_00416","title":"MasakhaNER: Named Entity Recognition for African Languages","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Google (Canada)","funders":"","keywords":"Computer science; Named-entity recognition; Variety (cybernetics); Natural language processing; Artificial intelligence; Representation (politics); Code (set theory); Quality (philosophy); Data science; Information retrieval; Programming language; Task (project management); Political science","authors":[{"name":"David Ifeoluwa Adelani","is_ca":false},{"name":"Jade Abbott","is_ca":false},{"name":"Graham Neubig","is_ca":false},{"name":"Daniel D’souza","is_ca":false},{"name":"Julia Kreutzer","is_ca":true},{"name":"Constantine Lignos","is_ca":false},{"name":"Chester Palen-Michel","is_ca":false},{"name":"Happy Buzaaba","is_ca":false},{"name":"Shruti Rijhwani","is_ca":false},{"name":"Sebastian Ruder","is_ca":false},{"name":"Stephen Mayhew","is_ca":false},{"name":"Israel Abebe Azime","is_ca":false},{"name":"Shamsuddeen Hassan Muhammad","is_ca":false},{"name":"Chris Chinenye Emezue","is_ca":false},{"name":"Joyce Nakatumba‐Nabende","is_ca":false},{"name":"Perez Ogayo","is_ca":false},{"name":"Anuoluwapo Aremu","is_ca":false},{"name":"Catherine Gitau","is_ca":false},{"name":"Derguène Mbaye","is_ca":false},{"name":"Jesujoba O. Alabi","is_ca":false},{"name":"Seid Muhie Yimam","is_ca":false},{"name":"Tajuddeen Gwadabe","is_ca":false},{"name":"Ignatius Ezeani","is_ca":false},{"name":"Rubungo Andre Niyongabo","is_ca":false},{"name":"Jonathan Mukiibi","is_ca":false},{"name":"Verrah Otiende","is_ca":false},{"name":"Iroro Orife","is_ca":false},{"name":"Davis David","is_ca":false},{"name":"Samba Ngom","is_ca":false},{"name":"Tosin Adewumi","is_ca":false},{"name":"Paul Rayson","is_ca":false},{"name":"Mofetoluwa Adeyemi","is_ca":false},{"name":"Gerald Muriuki","is_ca":false},{"name":"Emmanuel Anebi","is_ca":false},{"name":"Chiamaka Chukwuneke","is_ca":false},{"name":"Nkiruka Odu","is_ca":false},{"name":"Eric Peter Wairagala","is_ca":false},{"name":"Samuel Oyerinde","is_ca":false},{"name":"Clemencia Siro","is_ca":false},{"name":"Tobius Saul Bateesa","is_ca":false},{"name":"Temilola Oloyede","is_ca":false},{"name":"Yvonne Wambui","is_ca":false},{"name":"Victor Akinode","is_ca":false},{"name":"Deborah Nabagereka","is_ca":false},{"name":"Maurice Katusiime","is_ca":false},{"name":"Ayodele Awokoya","is_ca":false},{"name":"Mouhamadane Mboup","is_ca":false},{"name":"Dibora Gebreyohannes","is_ca":false},{"name":"Henok Tilaye","is_ca":false},{"name":"Kelechi Nwaike","is_ca":false},{"name":"Degaga Wolde","is_ca":false},{"name":"Abdoulaye Faye","is_ca":false},{"name":"Blessing Sibanda","is_ca":false},{"name":"Orevaoghene Ahia","is_ca":false},{"name":"Bonaventure F. P. Dossou","is_ca":false},{"name":"Kelechi Ogueji","is_ca":true},{"name":"Thierno Ibrahima Diop","is_ca":false},{"name":"Abdoulaye Baniré Diallo","is_ca":false},{"name":"Adewale Akinfaderin","is_ca":false},{"name":"Tendai Marengereke","is_ca":false},{"name":"Salomey Osei","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0247748537854371,"gpt":0.274549278675741,"spread":0.2497744248903039,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002995397,0.00007146581,0.0001228598,0.00004780295,0.0002264105,0.00005390561,0.0002470766,0.00006072634,0.000005390952],"category_scores_gemma":[0.001869988,0.0000714427,0.0001838769,0.0002182761,0.00001251399,0.00005027034,0.00001382188,0.00007257163,0.00000198714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195031,"about_ca_system_score_gemma":0.0001753815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001374625,"about_ca_topic_score_gemma":0.0000269326,"domain_scores_codex":[0.9990935,0.00004991873,0.0002752571,0.000180285,0.0002706065,0.0001304221],"domain_scores_gemma":[0.9969689,0.0009105659,0.0002503044,0.0001797331,0.001663971,0.00002657047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000045383,0.0006177434,0.001577006,0.0003284212,0.0005459526,0.000001036574,0.001832302,0.5917858,0.0004261813,0.3616296,0.001735535,0.03947499],"study_design_scores_gemma":[0.0009757116,0.00004475181,0.001273116,0.0000367397,0.0001340564,0.000002449673,0.0001353678,0.7804016,0.003815849,0.200266,0.01271559,0.0001986673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008115541,0.0000276095,0.995745,0.000957865,0.001097294,0.0002453187,0.0002995583,0.0000540844,0.0007617223],"genre_scores_gemma":[0.7305915,0.000002450735,0.2682015,0.00008969352,0.0001586911,0.00003445497,0.00006995219,0.000007012081,0.0008448005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7297799,"threshold_uncertainty_score":0.2913349,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312516176","doi":"10.1162/tacl_a_00511","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Columbia College","funders":"","keywords":"Causal inference; Computer science; Interpretability; Inference; Artificial intelligence; Causality (physics); Natural language processing; Robustness (evolution); Machine learning; Interpretation (philosophy); Data science; Econometrics","authors":[{"name":"Amir Feder","is_ca":false},{"name":"Katherine A. Keith","is_ca":false},{"name":"Emaad Manzoor","is_ca":false},{"name":"Reid Pryzant","is_ca":false},{"name":"Dhanya Sridhar","is_ca":true},{"name":"Zach Wood-Doughty","is_ca":false},{"name":"Jacob Eisenstein","is_ca":false},{"name":"Justin Grimmer","is_ca":false},{"name":"Roi Reichart","is_ca":false},{"name":"Margaret E. Roberts","is_ca":false},{"name":"Brandon Stewart","is_ca":false},{"name":"Victor Veitch","is_ca":false},{"name":"Diyi Yang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008751666553274558,"gpt":0.2654126314121237,"spread":0.2566609648588491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003941802,0.00007093567,0.0001008973,0.0001233042,0.0003168692,0.00004702772,0.0002557437,0.00002842414,0.000002414777],"category_scores_gemma":[0.0009841025,0.0000722758,0.00004290715,0.0003348594,0.0000183859,0.0001102657,0.00003591328,0.0001756872,2.204072e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002491818,"about_ca_system_score_gemma":0.0001593505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002313914,"about_ca_topic_score_gemma":0.00001817758,"domain_scores_codex":[0.9989764,0.00007125798,0.0003271464,0.0001689033,0.0003533844,0.0001028822],"domain_scores_gemma":[0.9986883,0.0005336072,0.0002607605,0.0001122602,0.0003871779,0.0000178934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008095644,0.00004575151,0.001715385,0.00002348255,0.0000133278,1.078577e-7,0.00266121,0.9693738,0.00001071988,0.01874815,0.00002380278,0.007376159],"study_design_scores_gemma":[0.0003364751,0.00002943389,0.005066474,0.00001024079,0.00001571947,0.000001365653,0.0001567182,0.974398,0.00002364614,0.0197674,0.0001321985,0.00006230678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005193481,0.00009538954,0.9929555,0.0004822177,0.0007656324,0.0002407088,0.00008363696,0.00004569585,0.0001377565],"genre_scores_gemma":[0.9406909,7.745049e-7,0.0589601,0.00008152298,0.00003035457,0.00004747977,0.00003173177,0.000005392746,0.0001517759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9354974,"threshold_uncertainty_score":0.2947322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3137010024","doi":"10.1162/tacl_a_00447","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":167,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Google (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Computer science; USable; Audit; Natural language processing; Quality (philosophy); Artificial intelligence; Information retrieval; World Wide Web; Accounting","authors":[{"name":"Julia Kreutzer","is_ca":true},{"name":"Isaac Caswell","is_ca":false},{"name":"Lisa Wang","is_ca":false},{"name":"Ahsan Wahab","is_ca":false},{"name":"Daan van Esch","is_ca":false},{"name":"Nasanbayar Ulzii-Orshikh","is_ca":false},{"name":"Allahsera Auguste Tapo","is_ca":false},{"name":"Nishant Subramani","is_ca":false},{"name":"Artem Sokolov","is_ca":false},{"name":"Claytone Sikasote","is_ca":false},{"name":"Monang Setyawan","is_ca":false},{"name":"Supheakmungkol Sarin","is_ca":false},{"name":"Sokhar Samb","is_ca":false},{"name":"Benoît Sagot","is_ca":false},{"name":"Clara E. Rivera","is_ca":false},{"name":"Annette Rios","is_ca":false},{"name":"Isabel Papadimitriou","is_ca":false},{"name":"Salomey Osei","is_ca":false},{"name":"Pedro Ortiz Suárez","is_ca":false},{"name":"Iroro Orife","is_ca":false},{"name":"Kelechi Ogueji","is_ca":true},{"name":"Andre Niyongabo Rubungo","is_ca":false},{"name":"Toan Nguyen","is_ca":false},{"name":"Mathias Müller","is_ca":false},{"name":"André Müller","is_ca":false},{"name":"Shamsuddeen Hassan Muhammad","is_ca":false},{"name":"N Sakib Muhammad","is_ca":false},{"name":"Ayanda Mnyakeni","is_ca":false},{"name":"Jamshidbek Mirzakhalov","is_ca":false},{"name":"Tapiwanashe Matangira","is_ca":true},{"name":"Colin Leong","is_ca":false},{"name":"Nze Lawson","is_ca":false},{"name":"Sneha Kudugunta","is_ca":false},{"name":"Yacine Jernite","is_ca":false},{"name":"Mathias Jenny","is_ca":false},{"name":"Orhan Fırat","is_ca":false},{"name":"Bonaventure F. P. Dossou","is_ca":false},{"name":"Sakhile Dlamini","is_ca":false},{"name":"Nisansa de Silva","is_ca":false},{"name":"Stella Biderman","is_ca":false},{"name":"Alessia Battisti","is_ca":false},{"name":"Ahmed Baruwa","is_ca":false},{"name":"Ankur Bapna","is_ca":false},{"name":"Pallavi Baljekar","is_ca":true},{"name":"Israel Abebe Azime","is_ca":false},{"name":"Ayodele Awokoya","is_ca":false},{"name":"Duygu Ataman","is_ca":false},{"name":"Orevaoghene Ahia","is_ca":false},{"name":"Oghenefego Ahia","is_ca":false},{"name":"Sweta Agrawal","is_ca":false},{"name":"Mofetoluwa Adeyemi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02197055172116473,"gpt":0.3306852318074935,"spread":0.3087146800863287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008875114,0.00009488399,0.0001897328,0.00008926034,0.0005031255,0.00002200382,0.0008587202,0.0000477147,0.00001285938],"category_scores_gemma":[0.001566438,0.00009121074,0.0001359563,0.0003749802,0.00003577304,0.00007443652,0.00009772754,0.0001745594,5.19751e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003728558,"about_ca_system_score_gemma":0.0002542236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004269242,"about_ca_topic_score_gemma":0.00003349575,"domain_scores_codex":[0.9983432,0.0001840854,0.0004607408,0.0002138657,0.0006618442,0.0001362973],"domain_scores_gemma":[0.9971779,0.0007856539,0.0007580015,0.0003375986,0.0009098315,0.00003099284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003399374,0.001879743,0.005995675,0.0003931012,0.0004356662,0.000001635489,0.003760186,0.7656395,0.004124791,0.2019991,0.005225493,0.01020511],"study_design_scores_gemma":[0.002193061,0.0003576371,0.003630752,0.00003403901,0.0001259193,0.000006118806,0.0001075539,0.8041309,0.01236331,0.1620325,0.01454772,0.0004705009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01121246,0.0001524962,0.9812422,0.0003335915,0.001485828,0.0004672054,0.004789886,0.0002091201,0.0001072298],"genre_scores_gemma":[0.7642645,7.697161e-7,0.2352252,0.00005920379,0.00005585414,0.00002500295,0.0002065392,0.000007330138,0.0001555747],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7530521,"threshold_uncertainty_score":0.3869685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1794039122","doi":"10.1162/tacl_a_00080","title":"Learning to Understand Phrases by Embedding the Dictionary","year":2016,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Compute Canada","keywords":"Computer science; Natural language processing; Word embedding; Artificial intelligence; Bridging (networking); Embedding; Lexical semantics; Semantics (computer science); Word (group theory); Task (project management); Linguistics; Lexical item","authors":[{"name":"Felix Hill","is_ca":false},{"name":"Kyunghyun Cho","is_ca":false},{"name":"Anna Korhonen","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01137076964757506,"gpt":0.2784432967756493,"spread":0.2670725271280742,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003648134,0.00008303657,0.00009171615,0.0000569358,0.0004958106,0.00005959518,0.0004999684,0.00005021749,0.000003448285],"category_scores_gemma":[0.001842179,0.00004813648,0.00009787539,0.0002967379,0.00003061111,0.00007766522,0.00002666008,0.0001074466,0.000002586404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002599624,"about_ca_system_score_gemma":0.00007722082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008315315,"about_ca_topic_score_gemma":0.000002818934,"domain_scores_codex":[0.9990501,0.00006549459,0.0002244915,0.0001535858,0.0003704159,0.0001359209],"domain_scores_gemma":[0.9972918,0.001694435,0.0002365958,0.0001480068,0.0005999867,0.00002917011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008869166,0.0003334202,0.001927171,0.00009295414,0.0004739467,5.855056e-7,0.005878478,0.3657968,0.00445762,0.5491351,0.03198768,0.0398276],"study_design_scores_gemma":[0.001343794,0.0004089774,0.0007551732,0.0003124187,0.0001790406,0.000007289225,0.0005124059,0.2000605,0.01893387,0.7295284,0.04732666,0.0006314726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004123395,0.00007215376,0.9943598,0.004122509,0.0004665031,0.0002072045,0.00007617656,0.0001456149,0.0001377283],"genre_scores_gemma":[0.86384,0.000003623922,0.1346106,0.0001638424,0.00007983595,0.00001326403,0.000004338168,0.000008536604,0.001275956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8634276,"threshold_uncertainty_score":0.3813424,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2179519966","doi":"10.1162/tacl_a_00104","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","year":2016,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Feature engineering; Feature (linguistics); Word (group theory); Artificial intelligence; Lexicon; Named-entity recognition; Task (project management); Natural language processing; Encoding (memory); State (computer science); Architecture; Entity linking; Deep learning; Knowledge base","authors":[{"name":"Jason Chiu","is_ca":true},{"name":"Eric Nichols","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02717742762268828,"gpt":0.2607877003144704,"spread":0.2336102726917821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004917182,0.0002052072,0.0002742988,0.000159353,0.0003289576,0.0001020883,0.0006733891,0.0002312499,0.000009888337],"category_scores_gemma":[0.000863964,0.0001621611,0.0002943136,0.000218486,0.00004399561,0.00007342455,0.0000729962,0.0003373063,0.000006957234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005519709,"about_ca_system_score_gemma":0.0005932096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003785249,"about_ca_topic_score_gemma":0.00003338543,"domain_scores_codex":[0.9979836,0.000106825,0.0005223708,0.000420194,0.0007569281,0.0002100508],"domain_scores_gemma":[0.9950942,0.0009232767,0.0009036153,0.0004040382,0.002623569,0.0000512341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007398837,0.0004107382,0.002493157,0.0003372116,0.0009733625,5.661178e-7,0.0005099511,0.8986678,0.00003352467,0.08651488,0.0009340167,0.009050834],"study_design_scores_gemma":[0.001135755,0.00008062233,0.002624327,0.0003635176,0.000288257,0.000003764626,0.00001117642,0.4125876,0.0006234305,0.577189,0.004629223,0.000463219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001055956,0.00002158433,0.9913074,0.001027224,0.003814213,0.0005396473,0.0008144261,0.0001377583,0.001281817],"genre_scores_gemma":[0.7926186,0.000007765815,0.2055044,0.00007299522,0.0005195515,0.000100538,0.0001081085,0.00002337927,0.001044683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7915626,"threshold_uncertainty_score":0.6612738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2570431255","doi":"10.1162/tacl_a_00077","title":"Aspect-augmented Adversarial Networks for Domain Adaptation","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Army Research Office","keywords":"Computer science; Adversarial system; Domain adaptation; Classifier (UML); Artificial intelligence; Transfer of learning; Sentence; Training set; Domain (mathematical analysis); Relevance (law); Natural language processing; Machine learning; Invariant (physics)","authors":[{"name":"Yuan Zhang","is_ca":true},{"name":"Regina Barzilay","is_ca":true},{"name":"Tommi Jaakkola","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02543341488488058,"gpt":0.2719049047599099,"spread":0.2464714898750293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004946559,0.00009524406,0.0001457923,0.00004891485,0.0009805651,0.0001372281,0.0007026093,0.00008707289,0.000001423809],"category_scores_gemma":[0.001332584,0.00009199788,0.0002082344,0.00007053823,0.00002826354,0.0001086269,0.00002320453,0.00009149282,8.974621e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001971995,"about_ca_system_score_gemma":0.0001350518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003009625,"about_ca_topic_score_gemma":0.00003133962,"domain_scores_codex":[0.9989459,0.00003602881,0.0003440489,0.0001990728,0.0003086508,0.0001662813],"domain_scores_gemma":[0.9971829,0.0006809731,0.0006928365,0.0003699666,0.001041239,0.00003206814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001900714,0.00003763592,0.0002095387,0.00001046002,0.00006814336,3.198407e-8,0.0001674859,0.8014472,0.00000469274,0.1968431,0.000112404,0.001080236],"study_design_scores_gemma":[0.0009980309,0.00003742903,0.001994108,0.00001442215,0.00004689369,2.585358e-7,0.00001917281,0.8939916,0.00004323882,0.09947993,0.003286947,0.00008790343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000243364,0.000009498177,0.994276,0.001022134,0.003304899,0.0005067077,0.00009330169,0.00004781438,0.0004962254],"genre_scores_gemma":[0.737249,0.000001126022,0.2619934,0.00004519403,0.0003425019,0.00003501998,0.00001933184,0.000008087794,0.0003063817],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7370056,"threshold_uncertainty_score":0.7541813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2185701500","doi":"10.1162/tacl_a_00239","title":"Measuring Machine Translation Errors in New Domains","year":2013,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Machine translation; Natural language processing; Domain (mathematical analysis); Phrase; Machine translation software usability; Artificial intelligence; Evaluation of machine translation; Porting; Example-based machine translation; Rule-based machine translation; Translation (biology); Programming language","authors":[{"name":"Ann Irvine","is_ca":false},{"name":"John Morgan","is_ca":false},{"name":"Marine Carpuat","is_ca":true},{"name":"Hal Daumé","is_ca":false},{"name":"Dragos Stefan Munteanu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02489167998879905,"gpt":0.2681288994135456,"spread":0.2432372194247465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002902656,0.00009296014,0.0001298541,0.0001376058,0.0001304476,0.00005985178,0.0004437771,0.00007732515,0.000005660943],"category_scores_gemma":[0.0005983054,0.00008207193,0.0001101756,0.0004354404,0.00001417735,0.000148804,0.00001070902,0.000153042,0.000003032959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002070497,"about_ca_system_score_gemma":0.0001655301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002539495,"about_ca_topic_score_gemma":0.0001051865,"domain_scores_codex":[0.9989555,0.00004755844,0.0003450801,0.000152819,0.0003541507,0.0001448285],"domain_scores_gemma":[0.9985641,0.00046169,0.0002602707,0.0001540034,0.0005262165,0.00003371488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003642566,0.0004440085,0.008568615,0.0002013625,0.00019926,6.153313e-7,0.003468418,0.5390531,0.001076243,0.3646112,0.001339159,0.08100156],"study_design_scores_gemma":[0.0007418247,0.00003569429,0.004412647,0.00005691333,0.00002819549,0.000001205751,0.00001234447,0.5488575,0.002077811,0.4425853,0.001014518,0.000176054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004474765,0.0001907287,0.9968857,0.001258779,0.0003947939,0.0003927506,0.00001834161,0.0001121558,0.0002992704],"genre_scores_gemma":[0.5807684,0.000001348525,0.4189285,0.00004525401,0.00003708514,0.00001179108,0.000006223426,0.000005908427,0.0001955121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.580321,"threshold_uncertainty_score":0.3346796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2799424953","doi":"10.1162/tacl_a_00018","title":"Questionable Answers in Question Answering Research: Reproducibility and Variability of Published Results","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Reproducibility; Computer science; Popularity; Reliability (semiconductor); Sample (material); Field (mathematics); Range (aeronautics); Code (set theory); Artificial intelligence; Data science; Statistics; Psychology; Mathematics; Social psychology","authors":[{"name":"Matt Crane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03935335336173296,"gpt":0.3372124674052018,"spread":0.2978591140434689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01194193,0.00007815933,0.0001828203,0.0001864756,0.000262208,0.00005541673,0.0003454961,0.00009912577,9.353631e-7],"category_scores_gemma":[0.02501033,0.00007229423,0.00006476821,0.0007528743,0.0001683729,0.0001359262,0.00003179788,0.0001744432,5.293787e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002983564,"about_ca_system_score_gemma":0.0002173248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004834671,"about_ca_topic_score_gemma":0.00009956647,"domain_scores_codex":[0.9976965,0.0004682724,0.0006501746,0.0004974864,0.000510078,0.0001775381],"domain_scores_gemma":[0.9936976,0.002086462,0.0003854324,0.0006454781,0.003148409,0.0000366158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002556212,0.0008296469,0.08088548,0.0003592137,0.0001288388,2.614372e-7,0.00666531,0.1441174,0.0006060645,0.7634407,0.001212427,0.001499018],"study_design_scores_gemma":[0.001540354,0.0003705999,0.1695891,0.0002595996,0.00002710918,0.000001795414,0.0001445967,0.3996072,0.002871558,0.4223044,0.00304046,0.0002432712],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04610717,0.00003354694,0.9450108,0.002623426,0.002328465,0.0008299167,0.000210907,0.00008359756,0.002772204],"genre_scores_gemma":[0.9599282,0.000002767869,0.03972273,0.000009646972,0.0001305943,0.00001607539,0.00001085968,0.000005334638,0.0001737846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.913821,"threshold_uncertainty_score":0.9832024,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226059645","doi":"10.1162/tacl_a_00471","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Minnow Environmental (Canada); Research Canada; Microsoft (Canada); McGill University","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Conversation; Computer science; Question answering; Open domain; Domain (mathematical analysis); Information retrieval; Interdependence; Natural language processing; Artificial intelligence; Relevance (law); Code (set theory); Linguistics; Set (abstract data type)","authors":[{"name":"Vaibhav Adlakha","is_ca":true},{"name":"Shehzaad Dhuliawala","is_ca":false},{"name":"Kaheer Suleman","is_ca":true},{"name":"Harm de Vries","is_ca":true},{"name":"Siva Reddy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01518758435261074,"gpt":0.2579240160992712,"spread":0.2427364317466605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006251952,0.00008483184,0.0001272042,0.00007006726,0.0008073392,0.00008607232,0.0007350856,0.00002849396,0.00001199987],"category_scores_gemma":[0.0001970824,0.00008025282,0.00007655113,0.0002680215,0.00001141874,0.0001107693,0.00008183779,0.000168213,6.321401e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004196202,"about_ca_system_score_gemma":0.0002498195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007153599,"about_ca_topic_score_gemma":0.00001775618,"domain_scores_codex":[0.9987488,0.000102055,0.0002918787,0.0002071946,0.0005162236,0.0001337964],"domain_scores_gemma":[0.9985244,0.0004337468,0.0003316965,0.0002057785,0.0004780396,0.00002635288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001103007,0.00004875907,0.001245457,0.000009972111,0.00004227079,1.610443e-7,0.0004062768,0.6655409,0.00001693351,0.3321195,0.00004215315,0.0005165403],"study_design_scores_gemma":[0.001399614,0.0001450334,0.004094598,0.00002409444,0.00005032672,0.000006773493,0.0001851201,0.8025433,0.0001291532,0.1759381,0.01526765,0.0002162224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004479512,0.000009144667,0.9917049,0.001450854,0.001070447,0.0003763602,0.00004969589,0.00004505117,0.0008140377],"genre_scores_gemma":[0.8094958,3.717986e-7,0.1897228,0.0001406722,0.00007873505,0.00005678426,0.00001577289,0.00000723056,0.0004818451],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8050163,"threshold_uncertainty_score":0.6209481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4398757454","doi":"10.1162/tacl_a_00667","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Mila - Quebec Artificial Intelligence Institute; Minnow Environmental (Canada); Research Canada","funders":"","keywords":"Correctness; Computer science; Question answering; Natural language processing; Artificial intelligence; Programming language","authors":[{"name":"Vaibhav Adlakha","is_ca":true},{"name":"Parishad BehnamGhader","is_ca":true},{"name":"Xing Han Lù","is_ca":true},{"name":"Nicholas Meade","is_ca":true},{"name":"Siva Reddy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03778902820660011,"gpt":0.3285510699647791,"spread":0.290762041758179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007699236,0.00008434834,0.00015215,0.0001057828,0.0002134809,0.00006618185,0.0001916228,0.00006318949,3.573119e-7],"category_scores_gemma":[0.0007533106,0.00008108369,0.0001544718,0.0002447588,0.00001686121,0.0001499504,0.00001421584,0.00008107107,9.965335e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001267515,"about_ca_system_score_gemma":0.0001532528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002465592,"about_ca_topic_score_gemma":0.000005163105,"domain_scores_codex":[0.9989496,0.00004338321,0.0003851098,0.0001987476,0.0003147357,0.000108447],"domain_scores_gemma":[0.9977589,0.001168447,0.0002052235,0.0001217265,0.0007253863,0.00002026614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004891626,0.00001269882,0.00007464747,0.0001369978,0.00006244984,2.58636e-8,0.0004174364,0.8073781,0.00005528296,0.1815955,0.000004424018,0.01025765],"study_design_scores_gemma":[0.0002811209,0.00003283201,0.0001393257,0.0001131828,0.00007535487,0.000001020297,0.00003366423,0.856438,0.000475256,0.1422618,0.000080665,0.00006773806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01619233,0.00008257401,0.9801859,0.0001559232,0.002853577,0.0003383785,0.00006211163,0.00006568449,0.00006357394],"genre_scores_gemma":[0.7754974,0.000001383816,0.2242914,0.000007629467,0.00008232595,0.00003225439,0.000007264649,0.000008556008,0.00007180391],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7593051,"threshold_uncertainty_score":0.3306497,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2769298630","doi":"10.1162/tacl_a_00011","title":"Modeling Past and Future for Neural Machine Translation","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Machine translation; Computer science; Decoding methods; Translation (biology); German; Artificial intelligence; Natural language processing; Mechanism (biology); Speech recognition; Machine learning; Algorithm; Linguistics","authors":[{"name":"Zaixiang Zheng","is_ca":false},{"name":"Hao Zhou","is_ca":false},{"name":"Shujian Huang","is_ca":false},{"name":"Lili Mou","is_ca":true},{"name":"Xinyu Dai","is_ca":false},{"name":"Jiajun Chen","is_ca":false},{"name":"Zhaopeng Tu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01634169044876612,"gpt":0.2815328401993656,"spread":0.2651911497505995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002611635,0.00008384592,0.0001062932,0.00006474793,0.0003456677,0.00005621154,0.0002529766,0.00007325257,7.257689e-7],"category_scores_gemma":[0.0001929896,0.00007112329,0.00009054879,0.0001788194,0.0000254442,0.00008350665,0.000008699598,0.00008121326,1.747645e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000572743,"about_ca_system_score_gemma":0.00004070944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008425446,"about_ca_topic_score_gemma":0.00001219162,"domain_scores_codex":[0.9992739,0.00002428516,0.0002343506,0.0001539149,0.0002009066,0.0001126633],"domain_scores_gemma":[0.9982671,0.0003059815,0.0001625264,0.0001116006,0.00113054,0.00002225712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001482603,0.0001956985,0.0004641765,0.0002356396,0.0002224423,1.199254e-7,0.002620172,0.3187037,0.0002610674,0.5493402,0.0004192555,0.1273893],"study_design_scores_gemma":[0.0003029204,0.00006176331,0.00004843361,0.000009314146,0.00003536963,9.226836e-7,0.000007593253,0.9146608,0.0002499123,0.08274306,0.001805808,0.00007415025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002366068,0.0003079817,0.9964927,0.001648284,0.0007440937,0.0003147929,0.000107442,0.0001002027,0.00004791327],"genre_scores_gemma":[0.5655377,0.000002020253,0.4339546,0.00006226112,0.0003811821,0.00001254278,0.0000132662,0.000005922686,0.00003053109],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.595957,"threshold_uncertainty_score":0.2900323,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4307680525","doi":"10.1162/tacl_a_00545","title":"Generative Spoken Dialogue Language Modeling","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Paralanguage; Computer science; Transformer; Spoken language; Generative grammar; Speech recognition; Natural language processing; Laughter; Language model; Artificial intelligence; Communication; Psychology","authors":[{"name":"Tu Anh Nguyen","is_ca":false},{"name":"Eugene Kharitonov","is_ca":false},{"name":"Jade Copet","is_ca":false},{"name":"Yossi Adi","is_ca":false},{"name":"Wei-Ning Hsu","is_ca":false},{"name":"Ali Elkahky","is_ca":false},{"name":"Paden Tomasello","is_ca":false},{"name":"Robin Algayres","is_ca":false},{"name":"Benoît Sagot","is_ca":false},{"name":"Abdelrahman Mohamed","is_ca":false},{"name":"Emmanuel Dupoux","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03106876500409547,"gpt":0.2777580017736145,"spread":0.246689236769519,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003788576,0.00007701094,0.00011996,0.0001190965,0.0002667954,0.00004750771,0.0003206098,0.00005777039,0.000006401258],"category_scores_gemma":[0.001192981,0.00006874448,0.0001683919,0.000494014,0.00001309841,0.00004848591,0.00001499508,0.00007721843,0.00002637584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009084,"about_ca_system_score_gemma":0.00009153716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001834511,"about_ca_topic_score_gemma":0.00001283945,"domain_scores_codex":[0.9990723,0.00005804852,0.0002562591,0.0001463827,0.0003277204,0.0001392757],"domain_scores_gemma":[0.9981995,0.0007700344,0.0001624226,0.0001479935,0.0006903863,0.00002961352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005890661,0.00005781431,0.0001247061,0.00001692951,0.0001034115,4.349561e-7,0.000975523,0.9443718,0.00009044241,0.04926354,0.0007801335,0.004209383],"study_design_scores_gemma":[0.0002326306,0.0000136682,0.0003395423,0.00000975468,0.00002707672,5.019593e-7,0.00006681948,0.9604092,0.0008483696,0.03725531,0.0007157958,0.00008129659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00261978,0.000008111875,0.9939814,0.0007426671,0.001041246,0.0001927447,0.0002275426,0.0001530527,0.001033427],"genre_scores_gemma":[0.896062,0.000004492444,0.1025423,0.0001129742,0.000162364,0.00002720898,0.00005087228,0.000009641694,0.001028244],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8934422,"threshold_uncertainty_score":0.2803318,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4296711106","doi":"10.1162/tacl_a_00506","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Spurious relationship; Benchmark (surveying); Attribution; Artificial intelligence; Natural language processing; Grounded theory; Data science; Machine learning; Qualitative research","authors":[{"name":"Nouha Dziri","is_ca":true},{"name":"Hannah Rashkin","is_ca":false},{"name":"Tal Linzen","is_ca":false},{"name":"David Reitter","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04673618613088275,"gpt":0.3095691801184852,"spread":0.2628329939876024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001894087,0.00007497027,0.0001235328,0.00008083235,0.0006922737,0.00004935094,0.0006068226,0.00003413863,0.000003645364],"category_scores_gemma":[0.0009724029,0.00006319057,0.0001121509,0.0004569704,0.00001601402,0.00004386479,0.00004913532,0.0002188384,8.195505e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006081125,"about_ca_system_score_gemma":0.0002137584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001125065,"about_ca_topic_score_gemma":0.00001866396,"domain_scores_codex":[0.9982984,0.0003008375,0.0004228133,0.0001732891,0.0006492363,0.0001554076],"domain_scores_gemma":[0.9974352,0.001385207,0.0003938719,0.0002358369,0.0005340975,0.00001582378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003683305,0.00003921397,0.0007819016,0.000009559121,0.00001896703,5.361912e-8,0.0003461091,0.8677119,0.000005948008,0.1305601,0.00007326783,0.0004493622],"study_design_scores_gemma":[0.0003558997,0.00004000152,0.003093898,0.000009873927,0.00002460541,0.000001259452,0.00008095613,0.9683258,0.00001170822,0.02505128,0.002936021,0.0000687051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004118812,0.0000582131,0.9912609,0.001261886,0.002447841,0.0005063805,0.0001513132,0.0000319609,0.0001627247],"genre_scores_gemma":[0.9821219,9.344745e-7,0.01730566,0.00006905398,0.0001326267,0.0001294092,0.00003198841,0.000005957642,0.0002024882],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9780031,"threshold_uncertainty_score":0.5324479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386488973","doi":"10.1162/tacl_a_00595","title":"<b>MIRACL</b>: A Multilingual Retrieval Dataset Covering 18 Diverse Languages","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Relevance (law); Natural language processing; Information retrieval; Process (computing); Quality (philosophy); Artificial intelligence; Resource (disambiguation); World Wide Web","authors":[{"name":"Xinyu Zhang","is_ca":true},{"name":"Nandan Thakur","is_ca":true},{"name":"Odunayo Ogundepo","is_ca":true},{"name":"Ehsan Kamalloo","is_ca":true},{"name":"David Alfonso-Hermelo","is_ca":true},{"name":"Xiaoguang Li","is_ca":false},{"name":"Mehdi Rezagholizadeh","is_ca":true},{"name":"Jimmy Lin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02744140968399567,"gpt":0.3310232120994008,"spread":0.3035818024154052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000502329,0.0001064053,0.0001412832,0.0001366012,0.0003151085,0.00007341236,0.0006532577,0.00008460315,0.000003617879],"category_scores_gemma":[0.002730084,0.00009632376,0.0001213397,0.0006405192,0.00003073275,0.0001005833,0.00006495441,0.0001592435,0.000008110082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535788,"about_ca_system_score_gemma":0.0001412078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001716639,"about_ca_topic_score_gemma":0.000006799247,"domain_scores_codex":[0.9988029,0.00003961305,0.0002858982,0.0002049256,0.0004793269,0.0001873578],"domain_scores_gemma":[0.9979218,0.000817857,0.0003114844,0.0002508848,0.0006646615,0.00003336797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007616745,0.0001995929,0.0007306366,0.0002137484,0.0002373939,0.000005007686,0.001668805,0.8884248,0.001054186,0.08216144,0.02018587,0.005042396],"study_design_scores_gemma":[0.0006211293,0.00004698206,0.0005479318,0.00004597185,0.00006715233,0.00000209255,0.00007361288,0.9226215,0.006450204,0.06412949,0.005160649,0.0002332672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001237391,0.00004949453,0.9942373,0.0003109883,0.0007573956,0.0002972409,0.002458527,0.0004875912,0.0001640916],"genre_scores_gemma":[0.7035652,0.000004043901,0.295231,0.0001034755,0.0001098044,0.00000837638,0.0003518782,0.00001327025,0.0006129894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7023278,"threshold_uncertainty_score":0.3927969,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196986263","doi":"10.1162/tacl_a_00519","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Interpretability; Computer science; Representation (politics); Artificial intelligence; Domain (mathematical analysis); Adaptation (eye); Interpretation (philosophy); Artificial neural network; Domain adaptation; Machine learning; Natural language processing; Data science; Neuroscience","authors":[{"name":"Hassan Sajjad","is_ca":true},{"name":"Nadir Durrani","is_ca":false},{"name":"Fahim Dalvi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05485884523086224,"gpt":0.2844312671001392,"spread":0.229572421869277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001004912,0.00009404695,0.000171686,0.0001359856,0.0004141737,0.00003064773,0.0007351246,0.00003713732,0.00000970963],"category_scores_gemma":[0.001517794,0.00009930883,0.0001733835,0.000644578,0.00003250706,0.0001094348,0.00005675721,0.000156789,0.000001463998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002691149,"about_ca_system_score_gemma":0.0001850884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001721563,"about_ca_topic_score_gemma":0.0001000492,"domain_scores_codex":[0.9982402,0.0002652663,0.0005298559,0.0001951726,0.0006146322,0.0001548797],"domain_scores_gemma":[0.9956962,0.001808541,0.000604507,0.0002472107,0.001615737,0.00002784106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002701781,0.0001336177,0.0002875109,0.00001435097,0.00004547857,6.749261e-8,0.0008840095,0.9043493,0.00001715231,0.09289635,0.00008256871,0.001262551],"study_design_scores_gemma":[0.0001410616,0.00009210363,0.00219451,0.00000466263,0.0000250496,6.813883e-7,0.00008269501,0.8927488,0.0003782526,0.1040206,0.0002306479,0.00008093096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001503547,0.00001935046,0.9958049,0.0002070149,0.001251807,0.0002977118,0.0004183423,0.00003560479,0.0004617078],"genre_scores_gemma":[0.9622099,0.000001445002,0.03735965,0.00007537704,0.00002758256,0.00004174737,0.00004126428,0.00001104868,0.0002320121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9607064,"threshold_uncertainty_score":0.4049696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4287120901","doi":"10.1162/tacl_a_00492","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada)","funders":"Defense Advanced Research Projects Agency","keywords":"Computer science; Artificial intelligence; Transformer; Natural language processing; Classifier (UML); Machine learning; Labeled data; Task (project management); Distillation; Language model","authors":[{"name":"Xuanli He","is_ca":false},{"name":"Islam Nassar","is_ca":false},{"name":"Jamie Kiros","is_ca":true},{"name":"Gholamreza Haffari","is_ca":false},{"name":"Mohammad Norouzi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01282966128692613,"gpt":0.2278401156433895,"spread":0.2150104543564634,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002956139,0.00007284671,0.0001048999,0.0000623304,0.0005657605,0.00004158121,0.0002870388,0.0000224848,0.000005390613],"category_scores_gemma":[0.0001709704,0.00006428565,0.00005468996,0.0002463946,0.00002223235,0.00003780467,0.00003140102,0.0001269165,6.010141e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001336795,"about_ca_system_score_gemma":0.000121653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002072119,"about_ca_topic_score_gemma":0.000006446199,"domain_scores_codex":[0.9990729,0.00006746583,0.0002041494,0.0001747528,0.0003644997,0.0001162437],"domain_scores_gemma":[0.998769,0.0004054737,0.0002118887,0.0001613785,0.0004274392,0.00002485121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007867027,0.00004727713,0.0005514655,0.00001119137,0.00004281405,1.68352e-7,0.0002747251,0.9435134,0.000009539143,0.05448517,0.00007760255,0.0009788168],"study_design_scores_gemma":[0.0004763199,0.0001083037,0.001067968,0.000007115237,0.00004526674,0.000007294013,0.00005647352,0.9713184,0.0001039498,0.01660016,0.01008966,0.0001190367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003172662,0.00004384595,0.9945679,0.000822044,0.0005367109,0.0002120451,0.00009536176,0.00004467748,0.0005047997],"genre_scores_gemma":[0.9206119,0.000001656359,0.07821162,0.00009229883,0.0000415479,0.00003213283,0.000007652599,0.000008229345,0.0009929793],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9174392,"threshold_uncertainty_score":0.4351429,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3198711991","doi":"10.1162/tacl_a_00478","title":"It’s not Rocket Science: Interpreting Figurative Language in Narratives","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Literal and figurative language; Computer science; Natural language processing; Principle of compositionality; Narrative; Generative grammar; Interpretation (philosophy); Artificial intelligence; Linguistics; Context (archaeology); Expression (computer science); Programming language; History","authors":[{"name":"Tuhin Chakrabarty","is_ca":false},{"name":"Yejin Choi","is_ca":false},{"name":"Vered Shwartz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01209388290123788,"gpt":0.3034295858987213,"spread":0.2913357029974835,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009717892,0.00008418872,0.0001253622,0.0002208324,0.0006501803,0.0000673199,0.000908902,0.00002872313,0.000008421675],"category_scores_gemma":[0.001728174,0.00007815174,0.00008506452,0.0009640958,0.00005987836,0.0001283973,0.00008742232,0.0002609201,4.526899e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000613291,"about_ca_system_score_gemma":0.0003327802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002027942,"about_ca_topic_score_gemma":0.00001374829,"domain_scores_codex":[0.998587,0.0001033229,0.0003117826,0.0002092827,0.0006233978,0.0001651894],"domain_scores_gemma":[0.9981942,0.0006131493,0.0003646727,0.0001587083,0.0006483546,0.00002091569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001200533,0.0006316968,0.00157045,0.0001088346,0.0001275751,0.00000332395,0.1198887,0.5001276,0.005457729,0.361055,0.002219938,0.008689185],"study_design_scores_gemma":[0.001321585,0.0003186107,0.001610948,0.0001306846,0.00003782655,0.000008971148,0.005927496,0.6409163,0.04257805,0.3013999,0.005165036,0.0005845756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003541789,0.00005465057,0.9899094,0.00397183,0.0009375658,0.0003818504,0.0001519146,0.0001149276,0.0009361233],"genre_scores_gemma":[0.8185074,2.954796e-7,0.1808597,0.0003276248,0.0000252759,0.00004508509,0.000007213672,0.000005424185,0.0002220223],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8149656,"threshold_uncertainty_score":0.5000727,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4381686872","doi":"10.1162/tacl_a_00564","title":"Questions Are All You Need to Train a Dense Passage Retriever","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"DeepMind","keywords":"Computer science; Initialization; Code (set theory); Task (project management); Set (abstract data type); Encoder; Artificial intelligence; Information retrieval; Scheme (mathematics); Training set; Domain (mathematical analysis); Language model; Natural language processing; Machine learning","authors":[{"name":"Devendra Singh Sachan","is_ca":true},{"name":"Dani Yogatama","is_ca":false},{"name":"Luke Zettlemoyer","is_ca":false},{"name":"Joëlle Pineau","is_ca":true},{"name":"Manzil Zaheer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03032712766975569,"gpt":0.2833717000899555,"spread":0.2530445724201998,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005935582,0.0001076164,0.0001592849,0.0001783604,0.0002773729,0.00006531456,0.0004944394,0.00008611333,0.00000288714],"category_scores_gemma":[0.002474759,0.0001054488,0.0001751254,0.0008877633,0.00001463214,0.00005545412,0.00002851556,0.0001330732,0.00002291463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002331363,"about_ca_system_score_gemma":0.0001335114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002653906,"about_ca_topic_score_gemma":0.00002188654,"domain_scores_codex":[0.9986047,0.0000709677,0.0003802735,0.00023298,0.0004897182,0.0002213543],"domain_scores_gemma":[0.9975826,0.0008448114,0.0002673519,0.0002863517,0.0009495089,0.00006942686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007530342,0.00005542348,0.000622758,0.00001862903,0.00007963835,5.109342e-7,0.0007630007,0.9242567,0.00003743697,0.07090283,0.00260139,0.000654098],"study_design_scores_gemma":[0.0005781777,0.0000456482,0.01313299,0.00004629962,0.00007954909,0.000001398406,0.0001052658,0.8803675,0.0001478213,0.0824341,0.0228431,0.0002181281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001841569,0.000005962389,0.9889662,0.00672966,0.001397282,0.0003583001,0.0002177889,0.0002163663,0.0002668287],"genre_scores_gemma":[0.8754216,0.000001953463,0.1216641,0.0003697265,0.0001663535,0.00004064702,0.00002391125,0.00001488026,0.002296746],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8735801,"threshold_uncertainty_score":0.4300076,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2605118633","doi":"10.1162/tacl_a_00047","title":"A Generative Model of Phonotactics","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Phonotactics; Computer science; Generative grammar; Artificial intelligence; Generative model; Feature (linguistics); Natural language processing; Set (abstract data type); Probabilistic logic; Phonology; Hierarchy; Linguistics; Programming language","authors":[{"name":"Richard Futrell","is_ca":false},{"name":"Adam Albright","is_ca":false},{"name":"Peter Graff","is_ca":false},{"name":"Timothy J. O’Donnell","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02717737201804962,"gpt":0.3050787880426549,"spread":0.2779014160246053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000254952,0.0000710305,0.0001338327,0.00004740572,0.0004332192,0.00006782914,0.0008270067,0.00006379435,6.292266e-7],"category_scores_gemma":[0.001986112,0.00006065244,0.0001278084,0.0000730001,0.00004730103,0.0001021635,0.00003260541,0.00009714454,3.162312e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009731935,"about_ca_system_score_gemma":0.0001747023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001576382,"about_ca_topic_score_gemma":0.000006034748,"domain_scores_codex":[0.9992197,0.00002148004,0.0002578238,0.0001157711,0.0002954049,0.00008984499],"domain_scores_gemma":[0.9969627,0.0003097801,0.0008362265,0.0003366906,0.001536774,0.0000178018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001138807,0.0001052077,0.0003088743,0.0000471498,0.00009422466,5.817966e-8,0.0004823906,0.3868974,0.0006765085,0.6096516,0.0002542349,0.001470869],"study_design_scores_gemma":[0.0001710755,0.00001875547,0.0001462283,0.00001526745,0.00002930266,2.056099e-7,0.00000287609,0.6603733,0.01723513,0.3218551,0.00009820362,0.00005454304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002897388,0.00002950201,0.9979694,0.0005573906,0.0004200153,0.0001538915,0.0001167386,0.00004162658,0.0004216756],"genre_scores_gemma":[0.539434,0.000001335833,0.4602677,0.00002297327,0.00002828194,0.000005270612,0.000002096928,0.000003581399,0.0002348488],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5391442,"threshold_uncertainty_score":0.3332015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313459318","doi":"10.1162/tacl_a_00529","title":"<scp>FaithDial</scp>: A Faithful Benchmark for Information-Seeking Dialogue","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Benchmark (surveying); Computer science; Utterance; Hallucinating; Natural language processing; Artificial intelligence; Crowdsourcing; Machine learning; World Wide Web","authors":[{"name":"Nouha Dziri","is_ca":true},{"name":"Ehsan Kamalloo","is_ca":true},{"name":"Sivan Milton","is_ca":true},{"name":"Osmar R. Zai͏̈ane","is_ca":true},{"name":"Mo Yu","is_ca":false},{"name":"Edoardo Maria Ponti","is_ca":false},{"name":"Siva Reddy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01280205941306425,"gpt":0.2332753737500383,"spread":0.220473314336974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007688726,0.0001161535,0.0001740415,0.0001578491,0.0009662766,0.0000965979,0.0007127409,0.00005648388,0.000003104415],"category_scores_gemma":[0.002465747,0.0001213055,0.0002528559,0.00040757,0.00001777358,0.0001732703,0.00005724137,0.0001745274,0.000001826298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000365542,"about_ca_system_score_gemma":0.0002969421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002490416,"about_ca_topic_score_gemma":0.000006852781,"domain_scores_codex":[0.9983848,0.00007455309,0.0005330361,0.0001780892,0.000602384,0.0002270817],"domain_scores_gemma":[0.9955707,0.002445505,0.0006061906,0.0002430055,0.001094459,0.00004010269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003870693,0.00005351169,0.0003907658,0.00003100511,0.00006741825,3.215052e-8,0.001184771,0.8315013,0.000003914636,0.1643453,0.001452838,0.0009652646],"study_design_scores_gemma":[0.0006946858,0.00007170009,0.0007840109,0.000007370297,0.00005338154,0.000001091683,0.0001227608,0.7987117,0.00004273238,0.0804075,0.1190299,0.00007315829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004796078,0.00001491426,0.9940663,0.0004397011,0.002188818,0.0006486871,0.000530003,0.00007777368,0.001554195],"genre_scores_gemma":[0.8601776,9.902162e-7,0.1385152,0.0002864749,0.0001934335,0.0002317682,0.0001394159,0.00001077723,0.0004443153],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.859698,"threshold_uncertainty_score":0.7431916,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2404429704","doi":"10.1162/tacl_a_00084","title":"Decoding Anagrammed Texts Written in an Unknown Language and Script","year":2016,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Intelligence, Security, War Strategy","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Decipherment; Computer science; Hebrew; Substitution (logic); Decoding methods; Natural language processing; Set (abstract data type); Cipher; Artificial intelligence; Identification (biology); Encryption; Speech recognition; Linguistics; Algorithm; Programming language","authors":[{"name":"Bradley Hauer","is_ca":true},{"name":"Grzegorz Kondrak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02373837580185808,"gpt":0.3242809997761862,"spread":0.3005426239743281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006853499,0.00006851428,0.0001126617,0.00009145037,0.0003289061,0.00003990847,0.0001687571,0.00008979296,0.00001254299],"category_scores_gemma":[0.001831264,0.00005491374,0.00006040082,0.0002251112,0.00009839463,0.00007421928,0.000005142998,0.00007418736,0.000002022124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002562462,"about_ca_system_score_gemma":0.0001523359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004046054,"about_ca_topic_score_gemma":0.005065025,"domain_scores_codex":[0.9989985,0.0001304085,0.0002557233,0.0001313458,0.0003016702,0.0001823519],"domain_scores_gemma":[0.9982991,0.0008343754,0.0001732893,0.00007558038,0.0005706816,0.00004700381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005421496,0.0003060609,0.04201183,0.00004385613,0.00008830494,8.603907e-7,0.02025182,0.01037744,0.0002015953,0.9064463,0.0001914378,0.02002627],"study_design_scores_gemma":[0.004327551,0.0003967386,0.1490344,0.0004237811,0.0003847105,0.000002163513,0.01577582,0.04484607,0.002527181,0.7388622,0.04217475,0.001244709],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5933885,0.0002622396,0.369254,0.007100028,0.004748152,0.002158409,0.0008510299,0.0002387012,0.02199892],"genre_scores_gemma":[0.995436,0.0000130891,0.003374538,0.00004160766,0.0001701645,0.000009965105,0.000007202342,0.00000804805,0.0009394137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4020475,"threshold_uncertainty_score":0.2826403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4317897852","doi":"10.1162/tacl_a_00539","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Naturalness; Natural language processing; Machine translation; Artificial intelligence; Modular design; Process (computing); Annotation; Benchmark (surveying); Information retrieval; Programming language","authors":[{"name":"Olga Majewska","is_ca":false},{"name":"Evgeniia Razumovskaia","is_ca":false},{"name":"Edoardo Maria Ponti","is_ca":false},{"name":"Ivan Vulić","is_ca":false},{"name":"Anna Korhonen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03988226869889792,"gpt":0.3194351972184415,"spread":0.2795529285195436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006989128,0.0001139956,0.0001445339,0.0001499214,0.0004317446,0.0001122431,0.0004639575,0.00009921613,0.000004669763],"category_scores_gemma":[0.001435833,0.0001104772,0.0001404615,0.0005200891,0.00002867721,0.00009701087,0.00002126347,0.0001133921,0.00001611472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001895357,"about_ca_system_score_gemma":0.0002098957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004506791,"about_ca_topic_score_gemma":0.00002749934,"domain_scores_codex":[0.9984911,0.00007447293,0.0004742575,0.000259493,0.000514315,0.0001863461],"domain_scores_gemma":[0.9974161,0.000776443,0.0003753901,0.0003241775,0.001069715,0.00003815059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005464336,0.00004807421,0.0008398361,0.00001767083,0.00003310909,1.44373e-7,0.0001113698,0.9836686,0.00007932082,0.01307408,0.0006838621,0.001438458],"study_design_scores_gemma":[0.0005223511,0.00002858853,0.001946123,0.000008184677,0.00003624488,3.387149e-7,0.000003605207,0.9784149,0.001056815,0.01331233,0.004559529,0.0001110164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002890198,0.000005653244,0.9924868,0.00064392,0.002102212,0.0003089657,0.001319559,0.0001523014,0.00009041908],"genre_scores_gemma":[0.9277753,0.000001261543,0.06892978,0.0001469178,0.00045218,0.0000352077,0.002279399,0.0000136869,0.0003662142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9248852,"threshold_uncertainty_score":0.450513,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3183195595","doi":"10.1162/tacl_a_00386","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Huawei Technologies (Canada)","funders":"","keywords":"Adversarial system; Focus (optics); Testbed; Named-entity recognition; Training set; Noise (video); Training (meteorology)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.0861111343750003,"gpt":0.2954547619652698,"spread":0.2093436275902695,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000693304,0.00009372538,0.0001970142,0.00007607152,0.000228355,0.00005819464,0.0002614815,0.0001111131,0.000004773474],"category_scores_gemma":[0.003625738,0.0001017544,0.0002179209,0.0002659278,0.00001916701,0.00008954848,0.00001602497,0.0001419275,0.00000108941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002959526,"about_ca_system_score_gemma":0.0004013327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003958949,"about_ca_topic_score_gemma":0.0001764161,"domain_scores_codex":[0.998693,0.000108775,0.0004549617,0.0002446176,0.0003250575,0.0001735547],"domain_scores_gemma":[0.9964706,0.001399694,0.0003380431,0.0001794613,0.001581309,0.00003085154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001066852,0.0005314706,0.002938704,0.0002225809,0.0003277532,0.000001426783,0.004344951,0.7570647,0.00007458376,0.1905416,0.0003083444,0.04353723],"study_design_scores_gemma":[0.001680068,0.00003212303,0.001833383,0.00006165829,0.00006014421,0.000001559263,0.0001703969,0.8222667,0.0005645643,0.1707774,0.002406139,0.0001458815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004614749,0.00001795619,0.9916773,0.0009005243,0.001958403,0.0003669694,0.0002951966,0.00004263799,0.0001262508],"genre_scores_gemma":[0.8654615,0.000001870407,0.133945,0.00009927167,0.0001644267,0.00003726227,0.00009067329,0.000007903566,0.000192093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8608468,"threshold_uncertainty_score":0.4340609,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394647506","doi":"10.1162/tacl_a_00670","title":"Scope Ambiguities in Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; National Research Council Canada; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Scope (computer science); Computer science; Linguistics; Cognitive science; Psychology; Programming language; Philosophy","authors":[{"name":"Gaurav Kamath","is_ca":true},{"name":"Sebastian Schuster","is_ca":false},{"name":"Sowmya Vajjala","is_ca":true},{"name":"Siva Reddy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02432477583018319,"gpt":0.2884349640007543,"spread":0.2641101881705711,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006891214,0.0001648432,0.0002673357,0.0002101269,0.0001119064,0.0001275178,0.0007808955,0.0002018387,0.000002375405],"category_scores_gemma":[0.0004853776,0.0001590203,0.0002747108,0.0002517656,0.00001693702,0.00003994545,0.0001996416,0.0005301927,0.000003907081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004270563,"about_ca_system_score_gemma":0.0004234529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001127005,"about_ca_topic_score_gemma":0.000102703,"domain_scores_codex":[0.9983252,0.00007481411,0.000554899,0.0003342984,0.0004977028,0.0002130634],"domain_scores_gemma":[0.9981161,0.0005063651,0.0003448258,0.0003790976,0.0006267565,0.00002690401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002047634,0.0000484877,0.00003005559,0.0001754659,0.00005735332,3.552575e-7,0.00122223,0.7876428,0.000001341837,0.2103863,0.0001253349,0.0003082244],"study_design_scores_gemma":[0.0001687564,0.000006501507,0.00008083854,0.0001368833,0.00003736827,2.406774e-7,0.00003763238,0.6484197,0.00003762421,0.3507294,0.0002464954,0.00009857232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001163186,0.0003863148,0.9907159,0.0006545199,0.003805688,0.0004511294,0.0006563903,0.0001107464,0.002056109],"genre_scores_gemma":[0.9117383,0.00001330506,0.08667691,0.00006985012,0.0002250666,0.00005485447,0.00004403695,0.00001927292,0.001158358],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9105752,"threshold_uncertainty_score":0.648466,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382449327","doi":"10.1162/tacl_a_00556","title":"Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Language model; Security token; Aggregate (composite); Exploit; Overhead (engineering); Encoder; Code (set theory); Artificial intelligence; Natural language processing; Set (abstract data type); Machine learning; Programming language","authors":[{"name":"Sheng-Chieh Lin","is_ca":true},{"name":"Minghan Li","is_ca":true},{"name":"Jimmy Lin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04200530028915431,"gpt":0.2897842792160807,"spread":0.2477789789269264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007641824,0.0001340794,0.0002046056,0.0001979086,0.0005237,0.00009802851,0.0006150194,0.00009964863,0.000001715385],"category_scores_gemma":[0.004222182,0.0001325927,0.0002633253,0.001193007,0.00002243005,0.00007790944,0.0000435334,0.000122691,0.000009434714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002264489,"about_ca_system_score_gemma":0.0002055364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002066875,"about_ca_topic_score_gemma":0.000007225321,"domain_scores_codex":[0.9982146,0.0000661476,0.0005064255,0.0003587545,0.0005632214,0.0002908403],"domain_scores_gemma":[0.996015,0.001691136,0.0003701218,0.0003691354,0.001477049,0.00007761773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002650593,0.00006915171,0.0002015348,0.00003287923,0.00008007375,1.122026e-7,0.0004465889,0.9290329,0.00002003662,0.0660539,0.003574841,0.0004615157],"study_design_scores_gemma":[0.0006675228,0.00005390431,0.001275707,0.00001340029,0.0000654806,0.000001012039,0.00009541114,0.9495025,0.00022149,0.04233556,0.005613443,0.0001545738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001233446,0.00000785228,0.9948376,0.0009467769,0.000750252,0.0009283886,0.0005282107,0.000191167,0.0005763167],"genre_scores_gemma":[0.6668717,0.000002389283,0.3304531,0.0001361737,0.0002372963,0.00008582233,0.0001615741,0.00002181582,0.002030134],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6656383,"threshold_uncertainty_score":0.5406973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3213458975","doi":"10.1162/tacl_a_00419","title":"<scp>ParsiNLU</scp>: A Suite of Language Understanding Challenges for Persian","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada); International Medias Data Services (Canada)","funders":"","keywords":"Computer science; Natural language understanding; Natural language processing; Suite; Benchmark (surveying); Artificial intelligence; Persian; Natural language; Linguistics","authors":[{"name":"Daniel Khashabi","is_ca":false},{"name":"Arman Cohan","is_ca":false},{"name":"Siamak Shakeri","is_ca":false},{"name":"Pedram Hosseini","is_ca":false},{"name":"Pouya Pezeshkpour","is_ca":false},{"name":"Malihe Alikhani","is_ca":false},{"name":"Moin Aminnaseri","is_ca":false},{"name":"Marzieh Bitaab","is_ca":false},{"name":"Faeze Brahman","is_ca":false},{"name":"Sarik Ghazarian","is_ca":false},{"name":"Mozhdeh Gheini","is_ca":false},{"name":"Arman Kabiri","is_ca":true},{"name":"Rabeeh Karimi Mahabagdi","is_ca":false},{"name":"Omid Memarrast","is_ca":false},{"name":"Ahmadreza Mosallanezhad","is_ca":false},{"name":"Erfan Noury","is_ca":false},{"name":"Shahab Raji","is_ca":false},{"name":"Mohammad Sadegh Rasooli","is_ca":false},{"name":"Sepideh Sadeghi","is_ca":false},{"name":"Erfan Sadeqi Azer","is_ca":false},{"name":"Niloofar Safi Samghabadi","is_ca":false},{"name":"Mahsa Shafaei","is_ca":false},{"name":"Saber Sheybani","is_ca":false},{"name":"Ali Tazarv","is_ca":false},{"name":"Yadollah Yaghoobzadeh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05384418972214958,"gpt":0.281614772268062,"spread":0.2277705825459125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003230425,0.00007847394,0.0001624632,0.00006850228,0.0001815772,0.0000290339,0.0002612984,0.00006853254,9.174919e-7],"category_scores_gemma":[0.002072148,0.00007971112,0.0002105552,0.0001902889,0.00001917119,0.00004565814,0.00001574799,0.00007239422,3.767705e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001984848,"about_ca_system_score_gemma":0.0001923109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005962239,"about_ca_topic_score_gemma":0.00001970116,"domain_scores_codex":[0.9990283,0.00004564069,0.0003003686,0.0001764726,0.0003039461,0.0001452741],"domain_scores_gemma":[0.9963433,0.002255487,0.000309124,0.0001749412,0.0008892635,0.00002789067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004644088,0.0001472854,0.0002860556,0.0002324545,0.0002289346,2.470431e-7,0.006186066,0.2768342,0.000110148,0.7147368,0.0001339006,0.001099342],"study_design_scores_gemma":[0.001307549,0.00008435754,0.001288887,0.0001188676,0.0001841204,0.000002659366,0.003221129,0.8253283,0.002388423,0.1633043,0.002663555,0.000107826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001672856,0.0002023314,0.9955479,0.0006329029,0.0007424006,0.0002166483,0.0001448069,0.00003172466,0.0008084133],"genre_scores_gemma":[0.8897815,0.00001004854,0.1095411,0.0000337926,0.00009859251,0.00001106632,0.00001648383,0.000008743681,0.0004986054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8881087,"threshold_uncertainty_score":0.3250525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2621376330","doi":"10.1162/tacl_a_00055","title":"Joint Modeling of Topics, Citations, and Topical Authority in Academic Corpora","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science, ICT and Future Planning","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Citation; Search engine indexing; Information retrieval; Process (computing); Joint (building); Generative grammar; Data science; Artificial intelligence; World Wide Web","authors":[{"name":"Jooyeon Kim","is_ca":true},{"name":"Dongwoo Kim","is_ca":false},{"name":"Alice Oh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07106014512581252,"gpt":0.318250592846475,"spread":0.2471904477206625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004619941,0.00006103636,0.0001506372,0.00006714269,0.0002436496,0.00003442957,0.0003748847,0.0000880679,5.708993e-7],"category_scores_gemma":[0.001880118,0.00005939988,0.00007151208,0.00006350628,0.0000324798,0.00008196546,0.0000336802,0.0001671056,1.788431e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000849045,"about_ca_system_score_gemma":0.0001014329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008015302,"about_ca_topic_score_gemma":0.00002417538,"domain_scores_codex":[0.9990754,0.00003563137,0.0004119432,0.0001403731,0.0002412849,0.00009534788],"domain_scores_gemma":[0.9985586,0.0002410533,0.0004191854,0.0002340909,0.0005232532,0.00002379704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004232249,0.00003629311,0.01244041,0.00004274265,0.00002139249,7.598566e-8,0.000398296,0.5883651,0.00001501283,0.3967745,0.000009792241,0.001892188],"study_design_scores_gemma":[0.0002708126,0.00001243014,0.02045474,0.00002814577,0.00001346266,2.875677e-7,0.00001464572,0.803604,0.00005185032,0.1754325,0.00007048487,0.00004662848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02197316,0.00002458694,0.9753662,0.001515569,0.0006601588,0.0001722212,0.000028229,0.00001311197,0.000246794],"genre_scores_gemma":[0.8918392,0.000006371423,0.1079484,0.00001845469,0.00007301617,0.00000594277,0.000002290992,0.000003170025,0.0001031612],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8698661,"threshold_uncertainty_score":0.2422257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3036116903","doi":"10.1162/tacl_a_00316","title":"Learning Lexical Subspaces in a Distributional Vector Space","year":2020,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Distributional semantics; Linear subspace; Artificial intelligence; Natural language processing; Similarity (geometry); Vector space; Word (group theory); Space (punctuation); Relation (database); Semantics (computer science); Semantic similarity; Suite; Code (set theory); Linguistics; Programming language; Data mining; Mathematics","authors":[{"name":"Kushal Arora","is_ca":true},{"name":"Aishik Chakraborty","is_ca":true},{"name":"Jackie Chi Kit Cheung","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01387567187832345,"gpt":0.2681135972948576,"spread":0.2542379254165342,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000233882,0.00008198959,0.000131857,0.00004650513,0.0001585188,0.00004953048,0.0003923585,0.00007105937,0.000002814784],"category_scores_gemma":[0.002845531,0.00007393916,0.0001075444,0.0004778953,0.00002514793,0.0000669315,0.00002281582,0.0002407528,0.000001748343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000174635,"about_ca_system_score_gemma":0.0001357632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000128929,"about_ca_topic_score_gemma":0.000005695196,"domain_scores_codex":[0.9990405,0.00006387007,0.0002471537,0.0001663206,0.0003482548,0.000133842],"domain_scores_gemma":[0.9984587,0.000642937,0.0002389261,0.0000752728,0.0005465141,0.00003768622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003882823,0.0001268299,0.006541947,0.00007877633,0.00005648837,7.748241e-7,0.001081908,0.2462142,0.0002692057,0.7443233,0.0005079906,0.0007598134],"study_design_scores_gemma":[0.0007952275,0.0001713885,0.005947527,0.00005705436,0.00003833609,0.000001558764,0.0000476996,0.8271922,0.004132099,0.1559251,0.005437665,0.0002541304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007746071,0.00006702999,0.9925947,0.005869948,0.0002300905,0.0001662771,0.00005970983,0.0001271125,0.0001105517],"genre_scores_gemma":[0.8169653,0.0000012942,0.1827545,0.00008987429,0.00008126389,0.00001002835,0.00001726722,0.000005269529,0.00007512144],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8161907,"threshold_uncertainty_score":0.3406571,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390037801","doi":"10.1162/tacl_a_00627","title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Benchmark (surveying); Computer science; Speech recognition; Domain (mathematical analysis); Set (abstract data type); Productivity; Natural language processing; Test set; Test (biology); Artificial intelligence; Biology","authors":[{"name":"Tobi Olatunji","is_ca":false},{"name":"Tejumade Afonja","is_ca":false},{"name":"Aditya Yadavalli","is_ca":false},{"name":"Chris Chinenye Emezue","is_ca":true},{"name":"Sahib Singh","is_ca":false},{"name":"Bonaventure F. P. Dossou","is_ca":true},{"name":"Joanne Osuchukwu","is_ca":false},{"name":"Salomey Osei","is_ca":false},{"name":"Atnafu Lambebo Tonja","is_ca":false},{"name":"Naome A. Etori","is_ca":false},{"name":"Clinton Mbataku","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05812305070298272,"gpt":0.3487872494558333,"spread":0.2906641987528506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001114227,0.0001191074,0.0002262917,0.0001375295,0.0003547458,0.0000871831,0.0004215704,0.0001079743,0.000006293557],"category_scores_gemma":[0.002235937,0.0001088157,0.0002118646,0.000477472,0.00005942516,0.00006553385,0.00003196935,0.0001138119,0.00001021098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007179853,"about_ca_system_score_gemma":0.000123009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001306607,"about_ca_topic_score_gemma":0.00001674859,"domain_scores_codex":[0.9984844,0.0001143187,0.0005347872,0.0002790425,0.0003719049,0.0002154905],"domain_scores_gemma":[0.9960313,0.002563846,0.0003467819,0.00023152,0.0007614666,0.00006503862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005093823,0.002140602,0.02217109,0.0004551674,0.002603493,0.00000748578,0.001513031,0.03347242,0.0002495657,0.3619883,0.3560663,0.2188231],"study_design_scores_gemma":[0.003128363,0.0001990988,0.03233039,0.00003914139,0.0002408775,0.000006851478,0.0001291899,0.5345359,0.0006791473,0.2051614,0.2230967,0.000452887],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004646251,0.00001277055,0.9822262,0.002400682,0.001841101,0.0007155606,0.00771043,0.0001354424,0.0003115977],"genre_scores_gemma":[0.3593456,0.00005278211,0.6367134,0.0004424211,0.0005730782,0.0001062088,0.001542805,0.00003146881,0.001192297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5010635,"threshold_uncertainty_score":0.4437374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285138469","doi":"10.1162/tacl_a_00487","title":"Heterogeneous Supervised Topic Models","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Office of Naval Research; Simons Foundation; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Computer science; Inference; Artificial intelligence; Outcome (game theory); Machine learning; Topic model; Bayes' theorem; Bayesian inference; Latent variable; Language model; Bayesian probability; Natural language processing; Probabilistic logic; Tone (literature); Linguistics","authors":[{"name":"Dhanya Sridhar","is_ca":true},{"name":"Hal Daumé","is_ca":false},{"name":"David M. Blei","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04311022111236518,"gpt":0.3237508931693172,"spread":0.280640672056952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008554866,0.00006227857,0.0001282668,0.00007776876,0.001573932,0.00002399307,0.00026322,0.00003367984,0.0001308687],"category_scores_gemma":[0.0006349026,0.00006355612,0.0002718547,0.0003929508,0.0000413357,0.0000259823,0.00001603247,0.0001095434,0.00000108819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000380406,"about_ca_system_score_gemma":0.0002715308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002249325,"about_ca_topic_score_gemma":0.00009579504,"domain_scores_codex":[0.9984648,0.0003088255,0.0002776756,0.0001204897,0.0006898881,0.0001383387],"domain_scores_gemma":[0.9976499,0.001203412,0.0002340324,0.00008528784,0.0007936546,0.00003370061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009354818,0.00007268327,0.0003046763,0.000004381412,0.00007489677,5.484512e-8,0.001082421,0.8695096,0.000001780148,0.1279194,0.0001497264,0.000870941],"study_design_scores_gemma":[0.0004479703,0.00004283109,0.0005759547,0.000003213326,0.000164935,4.421018e-7,0.0004929247,0.4539331,0.00002187395,0.4734356,0.07075175,0.0001294795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007819326,0.00008126294,0.9752662,0.002335436,0.002604886,0.0005898018,0.0004812233,0.00008167722,0.01074018],"genre_scores_gemma":[0.980868,0.000002916399,0.01507467,0.0001275672,0.0001873446,0.00004549582,0.00003598215,0.000008103453,0.003649909],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9730487,"threshold_uncertainty_score":0.9997259,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3208625967","doi":"10.1162/tacl_a_00427","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Government of Canada; National Endowment for the Humanities; National Science Foundation","keywords":"Computer science; Decoding methods; Optical character recognition; Consistency (knowledge bases); Artificial intelligence; Natural language processing; Language model; Raw data; Vocabulary; Error detection and correction; Machine learning; Speech recognition; Image (mathematics); Algorithm","authors":[{"name":"Shruti Rijhwani","is_ca":false},{"name":"Daisy Rosenblum","is_ca":true},{"name":"Antonios Anastasopoulos","is_ca":false},{"name":"Graham Neubig","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01389359865853384,"gpt":0.2640636733909112,"spread":0.2501700747323774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003921285,0.0001181406,0.0001850995,0.00009061831,0.000496484,0.00009705746,0.0003117512,0.0001229827,0.00001142456],"category_scores_gemma":[0.003247408,0.0001194742,0.0003161676,0.0003858344,0.00002075547,0.00009304576,0.00001996825,0.000185113,0.000003666884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002164537,"about_ca_system_score_gemma":0.0003438531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001090879,"about_ca_topic_score_gemma":0.00001573439,"domain_scores_codex":[0.9986709,0.0001021045,0.0004125609,0.0002509015,0.0003804115,0.0001830935],"domain_scores_gemma":[0.9929219,0.001556298,0.0003297672,0.0001768146,0.004972375,0.00004276812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001513071,0.001304283,0.003183178,0.0004848385,0.000916824,0.000001820339,0.002003108,0.7578551,0.003335119,0.1497678,0.009348501,0.07164813],"study_design_scores_gemma":[0.001000422,0.0002057548,0.001808251,0.00008038197,0.0001307388,0.000007247158,0.0001004478,0.9144182,0.02336099,0.04334361,0.01526807,0.0002759109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004082115,0.00001378683,0.9957113,0.0009731967,0.001661366,0.0003858138,0.0001251783,0.000207206,0.0005139672],"genre_scores_gemma":[0.8372139,0.000006473968,0.159342,0.0002586471,0.0002013475,0.0000968961,0.0001706499,0.00001939862,0.002690698],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8368057,"threshold_uncertainty_score":0.4872017,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3127907679","doi":"10.1162/tacl_a_00378","title":"A Computational Framework for Slang Generation","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Swearing, Euphemism, Multilingualism","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Slang; Natural language; Word (group theory); Interpretation (philosophy); Construct (python library); Inference; Meaning (existential); Probabilistic logic","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.04744032429022425,"gpt":0.3581615381772568,"spread":0.3107212138870326,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007008745,0.0001008814,0.0001711056,0.00005480978,0.00100668,0.00007972201,0.0001855367,0.0001763297,0.00003506966],"category_scores_gemma":[0.01130617,0.0001103084,0.0002698314,0.0003161484,0.00006867952,0.00004227667,0.000008015686,0.000136178,0.000003044407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004003027,"about_ca_system_score_gemma":0.0007646505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007288108,"about_ca_topic_score_gemma":0.0001749963,"domain_scores_codex":[0.9984584,0.0001221596,0.0004033437,0.0002069788,0.0005959271,0.000213193],"domain_scores_gemma":[0.9928963,0.003068926,0.0004190403,0.0001207251,0.003442726,0.00005227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001385612,0.0001169746,0.000671177,0.00002902398,0.0001286592,1.199644e-7,0.003262226,0.5458144,0.00003825209,0.4484687,0.0008678559,0.0005888382],"study_design_scores_gemma":[0.001372238,0.00004199215,0.002155165,0.00007323486,0.0003219236,0.000001077426,0.001360739,0.3079165,0.001415419,0.6108054,0.07419287,0.0003434689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004269757,0.00005079748,0.9891877,0.001595983,0.002570356,0.0005248074,0.0004660777,0.00006509836,0.001269408],"genre_scores_gemma":[0.7367666,0.000004827632,0.2599902,0.000203041,0.001085195,0.00005007612,0.0001930328,0.00001869097,0.001688274],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7324969,"threshold_uncertainty_score":0.997022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4221053465","doi":"10.1162/tacl_a_00458","title":"Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Inference; Generalization; Introspection; Spurious relationship; Machine learning; Rule of inference; Natural language; Natural (archaeology); Overfitting; Artificial neural network; Cognitive psychology","authors":[{"name":"Yufei Feng","is_ca":true},{"name":"Xiaoyu Yang","is_ca":true},{"name":"Xiaodan Zhu","is_ca":true},{"name":"Michael Greenspan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01236504266629197,"gpt":0.2721111208052126,"spread":0.2597460781389206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003000858,0.0001006974,0.00015177,0.00007863023,0.0005593154,0.0000475597,0.0005100151,0.00002596741,0.000003020078],"category_scores_gemma":[0.001183675,0.00008403201,0.000132589,0.0003180458,0.00001903474,0.00006060085,0.00004162686,0.0002334807,4.587802e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002973982,"about_ca_system_score_gemma":0.0001420389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001622546,"about_ca_topic_score_gemma":0.000009645544,"domain_scores_codex":[0.9988467,0.0000681696,0.0002587635,0.0002271063,0.000441139,0.0001581985],"domain_scores_gemma":[0.9972755,0.001337115,0.0003400169,0.0001989095,0.0008273078,0.00002113221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004167916,0.000072508,0.0003259231,0.0000287762,0.00006284696,2.321473e-7,0.0009319613,0.8032641,0.00004377042,0.1932195,0.0001317374,0.001876988],"study_design_scores_gemma":[0.0007117529,0.0001374396,0.001409075,0.00001182427,0.00004429512,0.000002812228,0.00009364087,0.9640448,0.0001061777,0.03169777,0.001610784,0.0001295945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002208699,0.00007158885,0.9944319,0.0009521377,0.001514728,0.0005296791,0.0001360505,0.00006601575,0.00008927295],"genre_scores_gemma":[0.890322,7.594388e-7,0.1089362,0.0002249046,0.000111588,0.00005202253,0.0000296727,0.000008863304,0.0003140533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8881133,"threshold_uncertainty_score":0.4301859,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394773742","doi":"10.1162/tacl_a_00645","title":"To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada)","funders":"","keywords":"Divergence (linguistics); Machine translation; Perspective (graphical); Computer science; Translation (biology); Artificial intelligence; Natural language processing; Diversity (politics); Linguistics; Sociology; Biology","authors":[{"name":"Jiaming Luo","is_ca":true},{"name":"Colin Cherry","is_ca":true},{"name":"George Foster","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0292461547114884,"gpt":0.3409946650393249,"spread":0.3117485103278365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004267047,0.0001859978,0.0002058206,0.0003467929,0.0004231673,0.0001774035,0.000535742,0.0001053777,0.00001407685],"category_scores_gemma":[0.0007301071,0.0001528258,0.0002097025,0.0009742859,0.00001675594,0.0001532413,0.00001914873,0.0002399644,0.00001373078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007004217,"about_ca_system_score_gemma":0.0001479669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001158343,"about_ca_topic_score_gemma":0.00008433926,"domain_scores_codex":[0.9982452,0.00007789834,0.0003969655,0.000389787,0.0006841073,0.0002060445],"domain_scores_gemma":[0.997525,0.001093367,0.0001554464,0.0002283438,0.0009220597,0.00007581787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007681038,0.0005528358,0.0001030638,0.0003328595,0.0005185981,0.000005541683,0.01427238,0.2984111,0.002780545,0.6481219,0.001883223,0.03224983],"study_design_scores_gemma":[0.001481306,0.00165415,0.002512637,0.0006220755,0.0005094534,0.000007981934,0.0001508632,0.7603824,0.01756227,0.2008457,0.01323232,0.001038786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005004664,0.0001016643,0.9908423,0.005623654,0.001068826,0.00079929,0.0004276235,0.0003708641,0.0002653498],"genre_scores_gemma":[0.7763106,0.000001794819,0.2227133,0.0003407014,0.0001267289,0.00004115572,0.00002524285,0.00001989793,0.0004205457],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7758102,"threshold_uncertainty_score":0.6232057,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115008472","doi":"10.1162/tacl_a_00233","title":"Distributional Semantics Beyond Words: Supervised Learning of Analogy and Paraphrase","year":2013,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Paraphrase; Natural language processing; Similarity (geometry); Artificial intelligence; Computer science; Analogy; Distributional semantics; Word (group theory); Tuple; Pairwise comparison; Noun; Function (biology); Noun phrase; Semantic similarity; Linguistics; Mathematics","authors":[{"name":"Peter D. Turney","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01650727852168584,"gpt":0.2569243560769647,"spread":0.2404170775552789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004547349,0.0001704476,0.000343922,0.0001309132,0.0002228003,0.00006530731,0.0005201662,0.000218964,0.000004980509],"category_scores_gemma":[0.001183257,0.0001671154,0.000239561,0.0001944444,0.00006609494,0.00004492329,0.0001178689,0.0004025252,7.75291e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001470503,"about_ca_system_score_gemma":0.0002902606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000565578,"about_ca_topic_score_gemma":0.000005997992,"domain_scores_codex":[0.9982619,0.0001169754,0.0006471943,0.000301221,0.0004980354,0.0001747319],"domain_scores_gemma":[0.995948,0.001182635,0.0008390858,0.000278256,0.001703799,0.00004820276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005641678,0.00007737151,0.003533009,0.0001809246,0.0001907401,9.234211e-8,0.0003559898,0.8270766,0.00001251374,0.1678716,0.00006916626,0.0006262732],"study_design_scores_gemma":[0.0003449974,0.0000291988,0.00348015,0.00006138639,0.0001198279,8.368723e-7,0.00002392214,0.8357258,0.00008851662,0.159591,0.0003953812,0.0001389886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01228212,0.0000973869,0.9849012,0.0005786795,0.001160313,0.0003747358,0.0004463468,0.00004049467,0.0001186586],"genre_scores_gemma":[0.8806467,0.00001996192,0.1188585,0.00002588593,0.0001161234,0.00002458863,0.0001465506,0.0000107461,0.0001509317],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8683646,"threshold_uncertainty_score":0.681477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400678062","doi":"10.1162/tacl_a_00678","title":"Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Conversation; Punctuation; Natural language processing; Benchmark (surveying); Attribution; Spurious relationship; Task (project management); Speech recognition; Artificial intelligence; Transcription (linguistics); Suite; Construct (python library); Linguistics; Psychology; Machine learning; Communication","authors":[{"name":"Cristina Aggazzotti","is_ca":false},{"name":"Nicholas Andrews","is_ca":false},{"name":"Elizabeth A. T. Smith","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04126170943162795,"gpt":0.2890382353474506,"spread":0.2477765259158227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001284655,0.0001480712,0.0001973636,0.0001969506,0.0002481107,0.0001414305,0.0004550224,0.0001531631,0.000004519271],"category_scores_gemma":[0.0008720792,0.0001409839,0.0002517613,0.0009661184,0.00003507323,0.0001202238,0.00001378768,0.0003370621,0.000003904358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005749023,"about_ca_system_score_gemma":0.0003179518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007318935,"about_ca_topic_score_gemma":0.0001077337,"domain_scores_codex":[0.9982116,0.0001481288,0.0005489645,0.0003031255,0.0005108243,0.0002774223],"domain_scores_gemma":[0.997973,0.0008604901,0.0001899306,0.0001958289,0.0007189525,0.0000617457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009986757,0.00005749702,0.0006129559,0.00008666189,0.00005262375,0.000001043218,0.001075135,0.3290814,0.00001855106,0.6671838,0.0001641117,0.001656216],"study_design_scores_gemma":[0.000262914,0.00002602803,0.002010627,0.00008797154,0.00004365476,0.000002142061,0.00002242694,0.6967576,0.0003692557,0.2968886,0.003390052,0.0001386819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001406393,0.0001016399,0.991105,0.002835135,0.002907874,0.0003794512,0.0003996857,0.0001679619,0.0006968419],"genre_scores_gemma":[0.9690908,0.000004606275,0.02990935,0.00006730719,0.0001574058,0.00002347971,0.00007339751,0.00001479927,0.0006588444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9676844,"threshold_uncertainty_score":0.5749155,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2774582842","doi":"10.1162/tacl_a_00076","title":"Joint Prediction of Word Alignment with Alignment Types","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Word (group theory); Artificial intelligence; Task (project management); Probabilistic logic; Natural language processing; Joint (building); Generative grammar; Pattern recognition (psychology)","authors":[{"name":"Anahita Mansouri Bigvand","is_ca":true},{"name":"Te Bu","is_ca":true},{"name":"Anoop Sarkar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01894919867233834,"gpt":0.2665170272751402,"spread":0.2475678286028018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003124765,0.00008165953,0.0001396725,0.00005360671,0.0003592146,0.0000632453,0.0005218115,0.00005400479,0.000001717123],"category_scores_gemma":[0.0005043264,0.00006219477,0.00009147352,0.00008231278,0.0000487978,0.00008571857,0.00002703086,0.0000757643,4.564853e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600528,"about_ca_system_score_gemma":0.0001035719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002881069,"about_ca_topic_score_gemma":0.000006582221,"domain_scores_codex":[0.9990051,0.00002530619,0.0002838768,0.0001385233,0.0004471032,0.0001001161],"domain_scores_gemma":[0.9977826,0.0001616452,0.0007833235,0.0003322767,0.000918414,0.00002173865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001197716,0.0007732883,0.008057245,0.0003771384,0.0008942732,9.375223e-7,0.001743412,0.2091468,0.001566111,0.7621713,0.001599712,0.01355007],"study_design_scores_gemma":[0.002579034,0.0006648917,0.03351029,0.0005550053,0.0004905857,0.000006429558,0.00006317074,0.272737,0.108196,0.575377,0.005325648,0.0004950041],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006449082,0.00004273621,0.9973396,0.0006159326,0.0005116659,0.0002672015,0.00012672,0.0000615514,0.0003896649],"genre_scores_gemma":[0.7041839,0.000002220457,0.2955016,0.00001816345,0.00004436417,0.00001361362,0.000006330564,0.000005241168,0.0002245122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.703539,"threshold_uncertainty_score":0.2762824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7086984966","doi":"10.1162/tacl.a.38","title":"Elements of World Knowledge (<scp>EWoK</scp>): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Schizophrenia research and treatment","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute","funders":"Quest for Intelligence, Massachusetts Institute of Technology; Yuhan","keywords":"Situated; Language model; Conceptual model; Domain knowledge; Simple (philosophy); Conceptual framework; Knowledge-based systems","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.04625059357637484,"gpt":0.3867130782903953,"spread":0.3404624847140204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006809917,0.0001404136,0.0003381455,0.0005329085,0.0001809124,0.00001567271,0.0001311821,0.00008196464,0.00000817421],"category_scores_gemma":[0.004389526,0.0001296965,0.0002806904,0.001030152,0.00004064945,0.000027641,0.00001302607,0.0002058895,0.000002552859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000481377,"about_ca_system_score_gemma":0.0007345375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002011318,"about_ca_topic_score_gemma":0.0006790148,"domain_scores_codex":[0.9984742,0.00009306655,0.0006381486,0.0002025556,0.0003564021,0.0002356349],"domain_scores_gemma":[0.9923193,0.005277524,0.0003402986,0.0001639657,0.001845659,0.00005328325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003656105,0.009133409,0.03150199,0.003483314,0.004862418,0.000001833367,0.005508846,0.2483558,0.000376326,0.6652368,0.003272965,0.02461015],"study_design_scores_gemma":[0.01258457,0.0003826045,0.02892273,0.001531951,0.001391677,4.707865e-7,0.0005070637,0.5304009,0.003561498,0.4196565,0.0009312079,0.0001289029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.104884,0.001567821,0.8662854,0.0009351855,0.001926601,0.006354967,0.002615128,0.0001197278,0.01531123],"genre_scores_gemma":[0.9097208,0.000005202445,0.08556057,0.00003919172,0.0001087052,0.0002719188,0.0002089466,0.00001873222,0.004065898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8048369,"threshold_uncertainty_score":0.5288868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417275930","doi":"10.1162/tacl.a.54","title":"The Impact of Automatic Speech Transcription on Speaker Attribution","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Attribution; Transcription (linguistics); Task (project management); Speaker diarisation; Phonetic transcription; Speech processing","authors":[{"name":"Cristina Aggazzotti","is_ca":false},{"name":"Matthew Wiesner","is_ca":false},{"name":"Elizabeth A. T. Smith","is_ca":true},{"name":"Nicholas Andrews","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01855258785467077,"gpt":0.296895449186917,"spread":0.2783428613322462,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006140794,0.0001025871,0.0001649026,0.0001197224,0.0003911645,0.00005434689,0.0004018506,0.00007545382,0.000007717594],"category_scores_gemma":[0.001182033,0.00007011711,0.0004120001,0.0005270405,0.00004285779,0.00004506929,0.000007165649,0.0001087238,0.000003789849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003402292,"about_ca_system_score_gemma":0.0002209559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000287611,"about_ca_topic_score_gemma":0.00001003857,"domain_scores_codex":[0.9987789,0.0001123159,0.0004543136,0.0001360543,0.0003774699,0.0001409427],"domain_scores_gemma":[0.9963386,0.001797346,0.0003815749,0.0002333609,0.001227295,0.00002184335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000120474,0.0008686565,0.001830245,0.0001288232,0.001096172,2.320689e-7,0.0003641318,0.2176661,0.000566499,0.6267067,0.00397746,0.1466746],"study_design_scores_gemma":[0.001001425,0.0001813449,0.05486301,0.000130588,0.0001545363,0.000001342425,0.00003102253,0.7963356,0.007274291,0.1364807,0.003390729,0.0001553716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005411647,0.00002125128,0.9895384,0.0008745218,0.001165434,0.0004167568,0.000165975,0.00005633581,0.002349617],"genre_scores_gemma":[0.9754187,0.000007753943,0.02370362,0.00004155175,0.00004261034,0.00001915064,0.00001430911,0.000005539405,0.0007467186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9700071,"threshold_uncertainty_score":0.3008561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399426318","doi":"10.1162/tacl_a_00669","title":"Source-Free Domain Adaptation for Question Answering with Masked Self-training","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Domain adaptation; Adaptation (eye); Domain (mathematical analysis); Question answering; Training (meteorology); Training set; Natural language processing; Artificial intelligence; Information retrieval; Speech recognition; Psychology","authors":[{"name":"M. Yin","is_ca":true},{"name":"Boyu Wang","is_ca":true},{"name":"Yue Dong","is_ca":false},{"name":"Charles X. Ling","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01946249239711238,"gpt":0.2532761076822381,"spread":0.2338136152851257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006295949,0.0001156597,0.0001399571,0.0001178218,0.0002954362,0.0001334556,0.0003817682,0.00007463119,7.56327e-7],"category_scores_gemma":[0.0004992173,0.0001020916,0.00014465,0.000300166,0.00001557799,0.0001211597,0.0000137615,0.000114937,8.780513e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002774742,"about_ca_system_score_gemma":0.0002645139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001705655,"about_ca_topic_score_gemma":0.00002794404,"domain_scores_codex":[0.9988038,0.00004584789,0.0003371657,0.0002485828,0.000386063,0.0001785457],"domain_scores_gemma":[0.997701,0.001091981,0.0002022992,0.000222808,0.000749401,0.00003247797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001123584,0.0000257552,0.00007441994,0.00009052434,0.0001090713,8.660268e-8,0.002521168,0.7838908,0.00001688898,0.2106347,0.00004257671,0.002582807],"study_design_scores_gemma":[0.0004515818,0.00006911642,0.0002087723,0.00008386564,0.00007655966,0.00000205497,0.0001257744,0.878799,0.00006065821,0.113734,0.006277318,0.0001113324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001064854,0.00003423189,0.9957943,0.0008533779,0.001201762,0.0004863207,0.00007673656,0.0002742602,0.0002141487],"genre_scores_gemma":[0.5237089,9.520993e-7,0.4758142,0.00002472953,0.0001591187,0.00004809091,0.00001424991,0.00001329585,0.0002164037],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5226441,"threshold_uncertainty_score":0.4163173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3206313044","doi":"10.1162/tacl_a_00441","title":"Quantifying Cognitive Factors in Lexical Decline","year":2021,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"German; Lexical diversity; Variety (cybernetics); Affect (linguistics); Cognition; Linguistics; Set (abstract data type); Logistic regression; Ecological niche; Psychology; Cognitive psychology; Computer science; Artificial intelligence; Ecology; Biology; Vocabulary; Communication","authors":[{"name":"David M. Francis","is_ca":true},{"name":"Ella Rabinovich","is_ca":true},{"name":"Farhan Samir","is_ca":true},{"name":"David R. Mortensen","is_ca":false},{"name":"Suzanne Stevenson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06521040049384863,"gpt":0.3677425165379125,"spread":0.3025321160440638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005678628,0.0001165469,0.0002376624,0.00006807679,0.0004053463,0.0000746341,0.0002035809,0.0002971781,0.00003075114],"category_scores_gemma":[0.006316827,0.0001042012,0.0003069724,0.0002608925,0.00006953016,0.00003356398,0.00003134874,0.0003674396,9.38981e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005444078,"about_ca_system_score_gemma":0.0006131089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001905921,"about_ca_topic_score_gemma":0.008131826,"domain_scores_codex":[0.9984391,0.0002205065,0.000410865,0.0001928746,0.0005600813,0.0001765938],"domain_scores_gemma":[0.9963778,0.001360499,0.0004486957,0.00007610411,0.00170063,0.00003623053],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.000108384,0.0009557565,0.104753,0.0003914998,0.0007207902,0.000001910131,0.05544528,0.7722772,0.00003173377,0.06360572,0.0003348449,0.00137379],"study_design_scores_gemma":[0.006422437,0.0002075155,0.5645517,0.003404655,0.003021711,0.000001259412,0.09295692,0.1055747,0.00157301,0.2027457,0.01687785,0.002662536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6604463,0.0006021264,0.311828,0.003017621,0.01191535,0.00269191,0.002369402,0.0001835801,0.006945722],"genre_scores_gemma":[0.9963481,0.00002525766,0.002294301,0.00005228386,0.0003151736,0.00002251613,0.0003890557,0.00001026449,0.0005429942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6667026,"threshold_uncertainty_score":0.7562288,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411934141","doi":"10.1162/tacl_a_00759","title":"A Comparative Approach for Auditing Multilingual Phonetic Transcript Archives","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Audit; Natural language processing; Linguistics; Speech recognition; Data science; Artificial intelligence; World Wide Web; Accounting; Business","authors":[{"name":"Farhan Samir","is_ca":true},{"name":"Emily P. Ahn","is_ca":false},{"name":"Shreya Prakash","is_ca":false},{"name":"Márton Sóskuthy","is_ca":true},{"name":"Vered Shwartz","is_ca":true},{"name":"Jian Zhu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03049783272393018,"gpt":0.2948096777967044,"spread":0.2643118450727742,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000279952,0.0001136531,0.0002294776,0.0001431088,0.0004108097,0.00005736129,0.0004006492,0.00006160774,0.000002206402],"category_scores_gemma":[0.0009694858,0.000104933,0.0003026233,0.0003175176,0.00004748826,0.00003762528,0.000008974721,0.000101494,7.271597e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008338026,"about_ca_system_score_gemma":0.0001882804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005179694,"about_ca_topic_score_gemma":0.000004361287,"domain_scores_codex":[0.9989284,0.00007520547,0.0003906063,0.000217972,0.0002217075,0.0001661146],"domain_scores_gemma":[0.996176,0.002657177,0.0002760736,0.00014659,0.0007164948,0.00002767563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000182405,0.001264987,0.0004004257,0.0004717041,0.001167542,1.416845e-7,0.005709879,0.6580609,0.0009451272,0.2933827,0.001534511,0.03687964],"study_design_scores_gemma":[0.001014834,0.00003819625,0.0009533112,0.00003854898,0.0001196358,5.059355e-7,0.0001714408,0.9388521,0.006983152,0.0483165,0.003387515,0.0001242887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000379382,0.0000273218,0.9929854,0.0003037706,0.000813693,0.0006261557,0.0002319399,0.00006548437,0.004566829],"genre_scores_gemma":[0.5785294,0.000001190477,0.4203424,0.00008290379,0.00005274732,0.00007776819,0.00002470258,0.000004551825,0.0008843202],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.57815,"threshold_uncertainty_score":0.4279042,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7114916806","doi":"10.1162/tacl.a.62","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Adversarial system; Adversary; Perspective (graphical); Training set; Memorization; Attack model","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.01430245061515127,"gpt":0.3394118539592187,"spread":0.3251094033440675,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005215677,0.0001374707,0.0001945677,0.0001661746,0.0005325443,0.00008026137,0.000636186,0.0001252481,0.000005143613],"category_scores_gemma":[0.003766231,0.0001335548,0.0001960838,0.0005812046,0.00005234641,0.0001684474,0.00003149633,0.0002625004,0.000001560548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007902506,"about_ca_system_score_gemma":0.0004632347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002179825,"about_ca_topic_score_gemma":0.00003003273,"domain_scores_codex":[0.9985347,0.0001437909,0.0003839767,0.0002928427,0.0004652686,0.0001793743],"domain_scores_gemma":[0.9962007,0.0009275091,0.0004253004,0.000308413,0.002099644,0.00003840398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002397498,0.00008025417,0.0001952496,0.00001384692,0.00008302106,1.238246e-7,0.000433967,0.6246652,0.000007860745,0.3736567,0.0001533554,0.0006863797],"study_design_scores_gemma":[0.0008216348,0.00005974794,0.00761136,0.00003115757,0.0001617074,9.735311e-7,0.0002733322,0.8221319,0.0001070688,0.165831,0.002819275,0.0001508175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002345632,0.00001339677,0.9902978,0.001832291,0.003384445,0.0003283721,0.00008495159,0.0001195697,0.003704646],"genre_scores_gemma":[0.8620734,0.000001713251,0.1366552,0.0001266174,0.0002637356,0.00002111933,0.00002840419,0.00001090654,0.000818901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8618389,"threshold_uncertainty_score":0.5446206,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416372001","doi":"10.1162/tacl.a.50","title":"Objectifying the Subjective: Cognitive Biases in Topic Interpretations","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Representativeness heuristic; Interpretation (philosophy); Salient; Cognitive bias; Quality (philosophy); Heuristics; Context (archaeology); Coherence (philosophical gambling strategy); Cognition","authors":[{"name":"Swapnil Hingmire","is_ca":false},{"name":"Ze Shi Li","is_ca":false},{"name":"Shiyu Zeng","is_ca":true},{"name":"Ahmed Musa Awon","is_ca":true},{"name":"Neil Ernst","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02274245253839106,"gpt":0.3057547969801711,"spread":0.28301234444178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004083251,0.00007549632,0.0001140907,0.0001323225,0.0002972237,0.0000552227,0.0003902423,0.00004962611,0.000001613349],"category_scores_gemma":[0.005029233,0.00005988994,0.0001199832,0.0005818768,0.00003042552,0.00005728954,0.0000236646,0.0001559024,9.287535e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002322242,"about_ca_system_score_gemma":0.0002448569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008242325,"about_ca_topic_score_gemma":0.0001609477,"domain_scores_codex":[0.999079,0.00009858641,0.0003238317,0.0001594382,0.0002070864,0.0001320973],"domain_scores_gemma":[0.9941946,0.004674987,0.0001908059,0.0001587728,0.000768732,0.00001213156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001012845,0.00009237645,0.007759156,0.00002284722,0.0001050536,9.780367e-8,0.001481706,0.8192902,0.000006784745,0.1676645,0.00004972922,0.003517384],"study_design_scores_gemma":[0.0005168439,0.0000185458,0.03330974,0.0001668725,0.00005944441,4.151779e-7,0.0002435469,0.8764617,0.0002978895,0.08840924,0.0004325226,0.00008321278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004096439,0.00004329795,0.9910735,0.001106034,0.001200813,0.000364375,0.00003658838,0.00003413301,0.002044816],"genre_scores_gemma":[0.9864897,0.000002416664,0.01262566,0.000192305,0.00004211275,0.00004791291,0.000005553131,0.000003842927,0.0005905411],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9823932,"threshold_uncertainty_score":0.6020826,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313459314","doi":"10.1162/tacl_a_00524","title":"The Emergence of Argument Structure in Artificial Languages","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Word order; Transitive relation; Predicate (mathematical logic); Natural language processing; Contrast (vision); Artificial intelligence; Argument (complex analysis); Sentence; Natural language; Relation (database); Object (grammar); Verb; Mathematics; Programming language","authors":[{"name":"Tom Bosc","is_ca":true},{"name":"Pascal Vincent","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0125030818935014,"gpt":0.2988419155317233,"spread":0.2863388336382219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004673041,0.00003584013,0.00006458729,0.00002453117,0.0008686617,0.000009643785,0.0001753816,0.00002570109,0.00006453884],"category_scores_gemma":[0.0008802375,0.0000266692,0.00007919663,0.0002727807,0.00004587643,0.0000151154,0.000007562503,0.00009222655,2.457977e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001703186,"about_ca_system_score_gemma":0.0001282098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005127078,"about_ca_topic_score_gemma":0.001962842,"domain_scores_codex":[0.9990637,0.0001344787,0.000225208,0.00005843442,0.0004226901,0.00009547989],"domain_scores_gemma":[0.9989393,0.0004110499,0.0002449899,0.00005414222,0.0003399539,0.00001060028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004390841,0.0001140789,0.002346295,0.00001321579,0.00006289427,9.998737e-8,0.01253122,0.6723009,0.0002200929,0.309402,0.0009909768,0.001974319],"study_design_scores_gemma":[0.001756696,0.0003114723,0.05637022,0.00005045192,0.0003942238,0.000001086458,0.1291862,0.04208656,0.002775945,0.5835451,0.1829176,0.0006043684],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8321181,0.002445139,0.07438308,0.02597017,0.02302963,0.00677711,0.007725867,0.0002311372,0.02731977],"genre_scores_gemma":[0.9985945,0.000006599138,0.0004411562,0.00002078831,0.0001062906,0.0000162564,0.00001864346,0.000002863114,0.0007928628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6302144,"threshold_uncertainty_score":0.6681131,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7128225249","doi":"10.1162/tacl.a.27","title":"Investigating Adversarial Trigger Transfer in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Adversarial system; Security token; Offensive; Robustness (evolution); Language model; Threat model; Language understanding","authors":[{"name":"Nicholas Meade","is_ca":false},{"name":"Arkil Patel","is_ca":false},{"name":"Siva Reddy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01217664085012492,"gpt":0.2804505190115679,"spread":0.2682738781614429,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007039987,0.0001064997,0.000187854,0.0001801754,0.0002465087,0.00004071211,0.0004957511,0.0001020365,0.000002861647],"category_scores_gemma":[0.001693452,0.0001032639,0.0001577944,0.0006825603,0.00002433973,0.0001111644,0.00002500827,0.0002571636,8.334024e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002576469,"about_ca_system_score_gemma":0.0002638574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005206128,"about_ca_topic_score_gemma":0.00004830924,"domain_scores_codex":[0.9987255,0.0001227523,0.000428612,0.0001992527,0.000328971,0.0001949527],"domain_scores_gemma":[0.9980693,0.001138681,0.0001508588,0.0001852582,0.0004330667,0.00002282755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005678086,0.00004992519,0.0007924619,0.00002173623,0.00003476313,8.61038e-8,0.0008322089,0.7214884,0.00001182322,0.2764742,0.0000423486,0.0002464317],"study_design_scores_gemma":[0.001299258,0.00001229619,0.001663238,0.00004733353,0.00003909627,1.446556e-7,0.00007316389,0.9168312,0.0001426082,0.07921344,0.0005862161,0.00009200824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001847487,0.00002163003,0.9939311,0.0007291547,0.001305853,0.0003017184,0.00005992154,0.00005891227,0.001744274],"genre_scores_gemma":[0.9368368,9.388809e-7,0.06225672,0.0001529149,0.00007603274,0.00001881908,0.00001389511,0.000007976543,0.0006358722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9349893,"threshold_uncertainty_score":0.421098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}