{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":11,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":11,"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":"34948cb5f57d","filters":{"venue":"Empirical Methods in Natural Language Processing"}},"results":[{"id":"W2117424365","doi":"","title":"Learning Noun Phrase Query Segmentation","year":2007,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"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; Query expansion; Web query classification; Query language; Natural language processing; RDF query language; Information retrieval; Artificial intelligence; Precision and recall; Web search query; Noun phrase; Sargable; Query optimization; Segmentation; Phrase; Set (abstract data type); Noun; Search engine","authors":[{"name":"Shane Bergsma","is_ca":true},{"name":"Qin Iris Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0283993285986766,"gpt":0.4422297324931074,"spread":0.4138304038944308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001764943,0.001461308,0.001360351,0.00255479,0.0009095654,0.00168334,0.00208545,0.001607709,0.004453001],"category_scores_gemma":[0.008356786,0.0005799825,0.001203247,0.0022644,0.0009504443,0.004833947,0.001263835,0.001394974,0.004793142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001798163,"about_ca_system_score_gemma":0.002716911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01032968,"about_ca_topic_score_gemma":0.01021331,"domain_scores_codex":[0.9975783,0.0005348501,0.0001939269,0.0009478871,0.000542721,0.0002022113],"domain_scores_gemma":[0.9960024,0.001954478,0.0003258212,0.000390885,0.001186548,0.0001399804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001223808,0.0008117332,0.01734042,0.00122203,0.0002690185,0.0008031325,0.001367993,0.05544667,0.1095561,0.0126512,0.06410027,0.7352076],"study_design_scores_gemma":[0.0001041952,0.0003907371,0.004715692,0.00005155077,0.00009915551,0.0004675289,0.000544894,0.924657,0.04218281,0.01156893,0.01515079,0.00006675308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2505085,0.002030118,0.6917123,0.001063335,0.000262982,0.001148817,0.006863247,0.036269,0.0101416],"genre_scores_gemma":[0.5606602,0.0005080543,0.4041167,0.000647672,0.0001913611,0.0005061697,0.02548356,0.0008227079,0.007063549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01032968,"threshold_uncertainty_score":0.02053916,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151839123","doi":"","title":"Translating Unknown Words by Analogical Learning","year":2007,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Lexicon; Computer science; Artificial intelligence; Natural language processing; Machine translation; Quality (philosophy); Translation (biology)","authors":[{"name":"Philippe Langlais","is_ca":true},{"name":"Alexandre Patry","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03097276130335845,"gpt":0.432158857636875,"spread":0.4011860963335165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002334547,0.0009315308,0.0008510428,0.001525126,0.0008260175,0.002036003,0.001801685,0.001534385,0.009029192],"category_scores_gemma":[0.01995533,0.0005088205,0.001195853,0.001564461,0.002620677,0.005196922,0.002849338,0.002304941,0.002127589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007952209,"about_ca_system_score_gemma":0.0007048314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008260214,"about_ca_topic_score_gemma":0.001105597,"domain_scores_codex":[0.9972542,0.001237975,0.0001774271,0.00081569,0.0004362707,0.00007846116],"domain_scores_gemma":[0.9905122,0.007023605,0.0004873798,0.001435234,0.0004559642,0.00008548981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002335248,0.0003457711,0.002485449,0.000696553,0.0002141264,0.0005272641,0.0009182912,0.06547508,0.007239574,0.1860284,0.007289914,0.728546],"study_design_scores_gemma":[0.00009675162,0.0001273142,0.0007754393,0.00006335229,0.00005342409,0.000424706,0.0002573359,0.3256868,0.004840369,0.6579227,0.009701287,0.00005043823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03419247,0.0005403067,0.9551979,0.0008488593,0.0001616158,0.0001424862,0.0001368224,0.0009328793,0.007846642],"genre_scores_gemma":[0.4625249,0.0007403221,0.5274295,0.0008527305,0.0003532822,0.0003279332,0.0008899785,0.0002751131,0.006606387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009029192,"threshold_uncertainty_score":0.03020561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W34986029","doi":"10.1089/cmb.2021.0438","title":"Exploiting Conversation Structure in Unsupervised Topic Segmentation for Emails","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":22,"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":"Latent Dirichlet allocation; Computer science; Topic model; Artificial intelligence; Natural language processing; Conversation; Segmentation; Exploit; Market segmentation; Thread (computing); Text segmentation; Information retrieval; Linguistics","authors":[{"name":"Shafiq Joty","is_ca":true},{"name":"Giuseppe Carenini","is_ca":true},{"name":"Gabriel Murray","is_ca":true},{"name":"Raymond T. Ng","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2587489947827946,"gpt":0.5735565170127669,"spread":0.3148075222299723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002732757,0.0007635469,0.0008066572,0.003993297,0.001026455,0.001350859,0.0008228426,0.001419546,0.001953487],"category_scores_gemma":[0.01166907,0.0004864434,0.0007776149,0.00164479,0.0007591173,0.002565441,0.001049733,0.001226282,0.00149955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001072829,"about_ca_system_score_gemma":0.001091656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004840827,"about_ca_topic_score_gemma":0.007943881,"domain_scores_codex":[0.998323,0.0007619077,0.00008100609,0.0004385739,0.0001958332,0.0001994865],"domain_scores_gemma":[0.9934228,0.004861163,0.0005407316,0.0003445669,0.0005888172,0.0002419019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00143887,0.0006650648,0.05062482,0.0005870352,0.0002458985,0.0003909521,0.003852312,0.1353786,0.0332248,0.01890531,0.0139189,0.7407674],"study_design_scores_gemma":[0.00002076429,0.00005787202,0.01044869,0.00003213785,0.00003092186,0.0001151868,0.0003847849,0.9657826,0.004934063,0.01550183,0.002656739,0.00003441056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3361197,0.001403931,0.6511336,0.000896129,0.000124056,0.0003041842,0.001312834,0.003110141,0.005595543],"genre_scores_gemma":[0.8661972,0.0002516952,0.1285883,0.00009874607,0.0001724036,0.0002021647,0.00203808,0.0002204974,0.002230914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004840827,"threshold_uncertainty_score":0.01445234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3213820586","doi":"","title":"How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding.","year":2021,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Adversarial Robustness in Machine Learning","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":"University of Waterloo; Queen's University","funders":"","keywords":"Robustness (evolution); Computer science; Adversarial system; Distillation; Artificial intelligence; Machine learning; Benchmark (surveying); Domain knowledge; Natural language; Artificial neural network; Theoretical computer science","authors":[{"name":"Tianda Li","is_ca":true},{"name":"Ahmad Rashid","is_ca":false},{"name":"Aref Jafari","is_ca":true},{"name":"Pranav Sharma","is_ca":false},{"name":"Ali Ghodsi","is_ca":true},{"name":"Mehdi Rezagholizadeh","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1018436876354653,"gpt":0.4440969145619636,"spread":0.3422532269264983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01273921,0.00147521,0.001116286,0.001803456,0.001022326,0.002132871,0.001763091,0.002141556,0.00312405],"category_scores_gemma":[0.05639349,0.0004408182,0.001116577,0.001440265,0.002997841,0.006609843,0.002055889,0.004038503,0.001127039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001286654,"about_ca_system_score_gemma":0.001245728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002915345,"about_ca_topic_score_gemma":0.003289579,"domain_scores_codex":[0.9921998,0.003666449,0.0004425801,0.001934038,0.001517523,0.0002395153],"domain_scores_gemma":[0.9638404,0.02859019,0.001181043,0.004717668,0.001289604,0.0003811133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007186966,0.0005284288,0.01774077,0.00125212,0.0008522728,0.0001718809,0.0003500491,0.3827002,0.003372689,0.05373875,0.02137095,0.5172032],"study_design_scores_gemma":[0.00006294808,0.0002698683,0.003425262,0.0002683597,0.000113061,0.0004560672,0.0003088182,0.8818595,0.006287686,0.09563284,0.01125111,0.00006451605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2339944,0.03146292,0.6979976,0.008438332,0.0005060991,0.0004465457,0.001418,0.002171747,0.0235643],"genre_scores_gemma":[0.854183,0.003561956,0.1357512,0.001123835,0.0001572087,0.0001339172,0.001777895,0.0003436557,0.002967439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01273921,"threshold_uncertainty_score":0.0673722,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1569397218","doi":"","title":"Utilizing Extra-Sentential Context for Parsing","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","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":"University of Toronto","funders":"","keywords":"Treebank; Parsing; Computer science; Natural language processing; Artificial intelligence; Context (archaeology); Consistency (knowledge bases); Conditional random field; Generative grammar; Set (abstract data type); Feature (linguistics); Linguistics; Programming language","authors":[{"name":"Jackie Chi Kit Cheung","is_ca":true},{"name":"Gerald Penn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05448447238682705,"gpt":0.4465676489612256,"spread":0.3920831765743986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003607569,0.001010597,0.0008795559,0.002387814,0.001252411,0.002524212,0.001193983,0.001174558,0.00295625],"category_scores_gemma":[0.01647549,0.001010086,0.0008056748,0.002118652,0.00110727,0.005743702,0.002036297,0.002147874,0.001127572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009030251,"about_ca_system_score_gemma":0.001999156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004363167,"about_ca_topic_score_gemma":0.01346379,"domain_scores_codex":[0.9971641,0.001287888,0.0001470554,0.0007259041,0.0005401171,0.0001349242],"domain_scores_gemma":[0.9904132,0.005982772,0.0005411411,0.002054213,0.0008802782,0.0001283804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007121082,0.0004203663,0.03085073,0.0006706361,0.000303706,0.001092777,0.002179008,0.1051839,0.0733434,0.06751309,0.01710697,0.7006233],"study_design_scores_gemma":[0.00007630782,0.0001627264,0.01305886,0.0001019088,0.0003014199,0.000717827,0.0003410002,0.7841001,0.05567835,0.1249592,0.02026481,0.0002375091],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2088213,0.0008720917,0.769417,0.0009804724,0.0001410972,0.000173587,0.001862617,0.0102099,0.007521971],"genre_scores_gemma":[0.7508827,0.0002648342,0.2439507,0.0001828699,0.00008836942,0.00009096759,0.001984204,0.001145414,0.001409975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004363167,"threshold_uncertainty_score":0.01907891,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089160253","doi":"","title":"Semantic Similarity Frontiers: From Concepts to Documents","year":2015,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Semantic similarity; Similarity (geometry); Semantics (computer science); Natural language processing; Information retrieval; Sentence; SemEval; Artificial intelligence; Word (group theory); Semantic computing; Component (thermodynamics); Semantic Web; Linguistics","authors":[{"name":"David Jurgens","is_ca":true},{"name":"Mohammad Taher Pilehvar","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07529857966887143,"gpt":0.4671359010380242,"spread":0.3918373213691527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007030482,0.001675001,0.001905911,0.01577358,0.002269715,0.01745799,0.003467682,0.00327376,0.01632308],"category_scores_gemma":[0.04153141,0.001069481,0.001853685,0.01596973,0.009744746,0.04408064,0.008495122,0.00471483,0.004286126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004879111,"about_ca_system_score_gemma":0.003480307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004052856,"about_ca_topic_score_gemma":0.001816256,"domain_scores_codex":[0.988965,0.00489536,0.0009885584,0.001958112,0.002778987,0.0004139937],"domain_scores_gemma":[0.9829217,0.0125178,0.0006683611,0.001527841,0.001751574,0.0006126796],"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":[0.0001283761,0.00006267778,0.0009319545,0.002040343,0.00009078026,0.0002175926,0.004306146,0.00205643,0.0008350895,0.7062044,0.02874314,0.2543831],"study_design_scores_gemma":[0.0000190685,0.00003541071,0.000801977,0.0006318014,0.00002357598,0.0003581519,0.001929103,0.006017998,0.0005252186,0.8562193,0.1334021,0.00003633168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01829769,0.1746842,0.6704322,0.03950157,0.003943226,0.0008234538,0.005100958,0.002508083,0.08470862],"genre_scores_gemma":[0.2613195,0.07543857,0.6234647,0.005949149,0.005360733,0.001702709,0.007486814,0.001346552,0.01793126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01745799,"threshold_uncertainty_score":0.0546062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2186073939","doi":"","title":"Sentiment Analysis of Social Media Texts","year":2014,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"SemEval; Computer science; Sentiment analysis; Negation; Lexicon; Task (project management); Artificial intelligence; Natural language processing; Focus (optics); Social media; Scope (computer science); World Wide Web","authors":[{"name":"Saif M. Mohammad","is_ca":false},{"name":"Xiaodan Zhu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03825425648608814,"gpt":0.4293544643095399,"spread":0.3911002078234517,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001756024,0.0008367223,0.0004867769,0.003602612,0.000549842,0.001871411,0.0002634877,0.0003982017,0.004304179],"category_scores_gemma":[0.007559821,0.0002162333,0.0006971795,0.00192128,0.0003236574,0.001487304,0.000667153,0.0005621551,0.003670833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004716175,"about_ca_system_score_gemma":0.0003972896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009733908,"about_ca_topic_score_gemma":0.001470174,"domain_scores_codex":[0.9981381,0.0005085015,0.0002066754,0.0002723219,0.0007665139,0.0001078839],"domain_scores_gemma":[0.9966654,0.001207646,0.0004171988,0.0001889236,0.00143337,0.00008745155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006617609,0.0001948659,0.03016832,0.001742166,0.0004414643,0.0005595179,0.001717482,0.004812416,0.1057356,0.004714197,0.07381459,0.7754376],"study_design_scores_gemma":[0.0001661455,0.000913941,0.1894905,0.0008176641,0.0005323698,0.001480925,0.005723152,0.3212771,0.1327253,0.03051522,0.3160769,0.0002807767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5346519,0.005686185,0.3233566,0.004219288,0.002749317,0.002135231,0.04133147,0.01076068,0.07510943],"genre_scores_gemma":[0.8001626,0.003671724,0.1411413,0.0008088594,0.001444446,0.0009512042,0.03168748,0.0009426532,0.01918984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004304179,"threshold_uncertainty_score":0.01439887,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3088099248","doi":"","title":"Memory Augmented Neural Networks for Natural Language Processing","year":2017,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","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 de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Scalability; Set (abstract data type); Focus (optics); Auxiliary memory; Deep learning; Machine learning; Theoretical computer science; Programming language","authors":[{"name":"Çağlar Gülçehre","is_ca":true},{"name":"Sarath Chandar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04028696249901548,"gpt":0.4603588160291883,"spread":0.4200718535301728,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003881671,0.0006802671,0.0005380233,0.0004555579,0.0002600349,0.001429541,0.001177947,0.001329491,0.008225783],"category_scores_gemma":[0.00168136,0.0002895037,0.0005790612,0.0008275581,0.0007551468,0.002462023,0.0008592088,0.002515746,0.001992282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009191722,"about_ca_system_score_gemma":0.000586267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002872325,"about_ca_topic_score_gemma":0.003583616,"domain_scores_codex":[0.9997805,0.00005574006,0.00001590259,0.00006147766,0.00006569506,0.00002074729],"domain_scores_gemma":[0.99972,0.0001556493,0.00002274373,0.00003983542,0.00005143516,0.00001022422],"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":[0.0001064211,0.00004813491,0.0003450635,0.000841338,0.0001242252,0.0001790689,0.0001333182,0.1240986,0.005683442,0.4699302,0.03125276,0.3672575],"study_design_scores_gemma":[0.00001065592,0.00003369576,0.0002274977,0.0001019693,0.00002183604,0.00008919403,0.00002512256,0.5015792,0.001764116,0.4447472,0.05137574,0.00002363938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005890888,0.02874634,0.9328775,0.003434018,0.0009876898,0.00007014274,0.0007113497,0.002375619,0.02490647],"genre_scores_gemma":[0.3558469,0.04099201,0.5375705,0.00172475,0.001840066,0.0006925424,0.002768675,0.0006264648,0.05793811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008225783,"threshold_uncertainty_score":0.02751791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2252227670","doi":"","title":"Resolving “This-issue†Anaphora","year":2012,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Anaphora (linguistics); Computer science; Natural language processing; Artificial intelligence; Resolution (logic)","authors":[{"name":"Varada Kolhatkar","is_ca":true},{"name":"Graeme Hirst","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07225211446287715,"gpt":0.4151775315217796,"spread":0.3429254170589024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0270473,0.0006308134,0.001316076,0.003577998,0.003477312,0.01025946,0.002770329,0.003664552,0.01146959],"category_scores_gemma":[0.1295,0.0008669135,0.001027381,0.003879197,0.003406222,0.01558231,0.008012157,0.004484918,0.001086088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001792166,"about_ca_system_score_gemma":0.003017935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001743492,"about_ca_topic_score_gemma":0.002029435,"domain_scores_codex":[0.9789256,0.01212706,0.001783143,0.003306428,0.003154786,0.0007029876],"domain_scores_gemma":[0.9250197,0.05646777,0.004487348,0.01003754,0.003493107,0.0004945516],"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":[0.0002817865,0.0002847794,0.02482865,0.0006210641,0.0002448396,0.0004418227,0.004163137,0.002292797,0.001935671,0.7701298,0.01247398,0.1823016],"study_design_scores_gemma":[0.00008060931,0.00003279401,0.009405055,0.0002922257,0.0001403984,0.000950702,0.00314721,0.02450635,0.004227859,0.9149805,0.04217871,0.00005763003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3284802,0.004578263,0.5699951,0.02468083,0.001455832,0.0003703665,0.001891879,0.0009254813,0.06762195],"genre_scores_gemma":[0.8662112,0.0009495942,0.1220369,0.001414387,0.0007314433,0.0001588894,0.001906634,0.0004304611,0.006160398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0270473,"threshold_uncertainty_score":0.1430416,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044276988","doi":"","title":"Low-Resource Neural Network Modelling for Universal Dependency Parsing","year":2015,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Parsing; Dependency grammar; Dependency (UML); Artificial neural network; Artificial intelligence; Resource (disambiguation); Natural language processing; Computer network","authors":[{"name":"Long Duong","is_ca":false},{"name":"Trevor Cohn","is_ca":false},{"name":"Steven Bird","is_ca":false},{"name":"Paul Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07949367515106834,"gpt":0.4100113437268794,"spread":0.330517668575811,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001786331,0.0006737505,0.001150602,0.0009108463,0.0006451018,0.001793298,0.002459677,0.001688365,0.007228578],"category_scores_gemma":[0.01206516,0.0009019778,0.0009257125,0.001468855,0.0009003588,0.005081753,0.001585434,0.003157302,0.001105536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001371757,"about_ca_system_score_gemma":0.001383697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009068697,"about_ca_topic_score_gemma":0.0151448,"domain_scores_codex":[0.9994619,0.000262005,0.00003150475,0.000127126,0.00005797524,0.00005945075],"domain_scores_gemma":[0.996483,0.002803084,0.0001045638,0.000351851,0.000189343,0.00006813741],"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":[0.0001078998,0.00005428618,0.0007181022,0.0001166479,0.00007244438,0.0001267589,0.0001138327,0.8091813,0.001143907,0.1397471,0.002964171,0.04565349],"study_design_scores_gemma":[0.000002531635,0.000001709639,0.00005109473,0.000004036858,0.000004825182,0.000006936749,0.0000033349,0.9490854,0.0001109606,0.05054218,0.0001839109,0.000003101427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02560513,0.0004439971,0.9689622,0.0005397766,0.00006158111,0.00002604315,0.0003944987,0.0006934858,0.003273358],"genre_scores_gemma":[0.7781634,0.0007257033,0.2084505,0.0002156602,0.0001307419,0.0002397913,0.001308554,0.0007139595,0.01005172],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009068697,"threshold_uncertainty_score":0.02418202,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996912688","doi":"","title":"Discreteness in Neural Natural Language Processing","year":2019,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","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 Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Focus (optics); Process (computing); Point (geometry); Space (punctuation); Natural language processing; Natural language; Machine learning; Programming language; Mathematics","authors":[{"name":"Lili Mou","is_ca":true},{"name":"Hao Zhou","is_ca":false},{"name":"Lei Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03199366781166351,"gpt":0.4167666648137828,"spread":0.3847729970021193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002696853,0.0006411536,0.0008731439,0.001451712,0.0005170694,0.003094788,0.001273792,0.001437101,0.005647586],"category_scores_gemma":[0.008808486,0.00055805,0.0008259129,0.002033613,0.003438078,0.007027759,0.00167771,0.004527737,0.001170104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001709879,"about_ca_system_score_gemma":0.0009223366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001710346,"about_ca_topic_score_gemma":0.001486802,"domain_scores_codex":[0.9986045,0.0005509247,0.0001267985,0.0002790199,0.0003788133,0.00006007013],"domain_scores_gemma":[0.9967226,0.002725398,0.0001036021,0.0002288769,0.0001648482,0.00005470367],"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":[0.000008682474,0.00001257172,0.0001717305,0.0001868056,0.00001803061,0.00004403601,0.0001196462,0.008050798,0.0002956744,0.9580468,0.00289331,0.03015183],"study_design_scores_gemma":[0.000002290688,0.000006364479,0.0001062196,0.00006262793,0.000003687678,0.00004674579,0.00001719637,0.0318422,0.0001793849,0.9566795,0.0110448,0.000008947861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003614689,0.02525586,0.943899,0.004830928,0.0004760487,0.00004962716,0.0003468149,0.0002985745,0.02122846],"genre_scores_gemma":[0.3193847,0.06627134,0.5783498,0.003323009,0.003965212,0.0007999758,0.001453182,0.0004947727,0.025958],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005647586,"threshold_uncertainty_score":0.01889312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}