{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":10,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":10,"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":"ab38acd60060","filters":{"venue":"International Joint Conference on Natural Language Processing"}},"results":[{"id":"W2250473310","doi":"","title":"Can I Hear You? Sentiment Analysis on Medical Forums","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Lexicon; Sentiment analysis; Computer science; Annotation; Natural language processing; World Wide Web; Information retrieval; Artificial intelligence","authors":[{"name":"Tanveer Ali","is_ca":true},{"name":"David Schramm","is_ca":false},{"name":"Marina Sokolova","is_ca":true},{"name":"Diana Inkpen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01899128694098449,"gpt":0.2948058488755669,"spread":0.2758145619345824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003311815,0.0002738389,0.0003385527,0.003495226,0.0008559614,0.0009251354,0.0001904268,0.0003030046,0.001398791],"category_scores_gemma":[0.01072813,0.00008568574,0.0002508996,0.001749288,0.0003518571,0.0008467372,0.0006494611,0.0003622691,0.0004445503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004509384,"about_ca_system_score_gemma":0.000274309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009560575,"about_ca_topic_score_gemma":0.001508989,"domain_scores_codex":[0.9979929,0.0009316658,0.0001889443,0.0001944795,0.0005116315,0.0001803249],"domain_scores_gemma":[0.9863728,0.007988187,0.001985167,0.0002760758,0.002959279,0.0004185534],"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":[0.002207632,0.0004557323,0.3342931,0.002001528,0.0002205022,0.002207986,0.05380911,0.001538192,0.1823903,0.003952674,0.02874043,0.3881828],"study_design_scores_gemma":[0.00007616109,0.0007347006,0.803687,0.0005639233,0.0002048619,0.001417193,0.03760966,0.05241516,0.03716848,0.005417144,0.06054847,0.0001572207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834006,0.0003656118,0.006911651,0.0005919447,0.0001844312,0.0001864117,0.002513522,0.0001275206,0.005718272],"genre_scores_gemma":[0.9853695,0.0002272729,0.009963064,0.0001475232,0.0002694447,0.0001751702,0.002043502,0.00004698126,0.001757508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003495226,"threshold_uncertainty_score":0.01751477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2773368817","doi":"","title":"Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"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":"Recurrent neural network; Benchmark (surveying); Feature engineering; Computer science; Artificial intelligence; Machine learning; Feature (linguistics); Artificial neural network; Long short term memory; Term (time); Deep learning","authors":[{"name":"Yu Lun Hsieh","is_ca":false},{"name":"Yung‐Chun Chang","is_ca":true},{"name":"Wen Lian Hsu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04678864868712887,"gpt":0.357966264190523,"spread":0.3111776155033941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001421592,0.001086755,0.0008847273,0.003709899,0.0003958071,0.0009311102,0.001388831,0.000978357,0.001230949],"category_scores_gemma":[0.004515251,0.0003286115,0.0009205429,0.00342421,0.0003071533,0.001757272,0.0009218503,0.0007417423,0.001252654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005989482,"about_ca_system_score_gemma":0.0008767934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004805171,"about_ca_topic_score_gemma":0.01073587,"domain_scores_codex":[0.9991828,0.0001785191,0.0001081556,0.0002402521,0.0002169274,0.00007340082],"domain_scores_gemma":[0.9983836,0.0007645624,0.0003201543,0.0001427039,0.000347316,0.00004160461],"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":[0.0005862569,0.000505438,0.01870609,0.001394065,0.0009206695,0.001258474,0.0003339626,0.100407,0.03872592,0.003402987,0.01355746,0.8202017],"study_design_scores_gemma":[0.00002235599,0.0001507877,0.005765753,0.00008700196,0.0003349533,0.0004387833,0.00008741031,0.9700664,0.0112597,0.006784759,0.00496367,0.00003845241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2190628,0.02058863,0.7394633,0.001854301,0.0004266137,0.0002865056,0.004654321,0.007838719,0.005824819],"genre_scores_gemma":[0.7946433,0.004969976,0.184429,0.0007007477,0.0004536123,0.0003051086,0.009959215,0.0001414437,0.004397524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004805171,"threshold_uncertainty_score":0.009554446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2775747321","doi":"","title":"WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","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":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Information retrieval; Artificial intelligence; Quality (philosophy); Named-entity recognition; Simple (philosophy); Training set; Range (aeronautics); Task (project management)","authors":[{"name":"Abbas Ghaddar","is_ca":false},{"name":"Phillippe Langlais","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06018724801345868,"gpt":0.3217091971620433,"spread":0.2615219491485846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001937892,0.001156001,0.0007606663,0.008492736,0.001331907,0.001221952,0.001727385,0.001216258,0.008344822],"category_scores_gemma":[0.01009449,0.0006307687,0.00062842,0.005291368,0.0005276428,0.003341444,0.001665736,0.001686168,0.006529647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005825823,"about_ca_system_score_gemma":0.002104229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008997921,"about_ca_topic_score_gemma":0.01863313,"domain_scores_codex":[0.9978318,0.0005427693,0.0003503999,0.0006255205,0.0005258772,0.0001236432],"domain_scores_gemma":[0.9922423,0.002378907,0.0006464412,0.001584079,0.002659208,0.0004891221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005942069,0.000692555,0.01005735,0.0038305,0.0002397882,0.001839053,0.001586921,0.006727236,0.03953732,0.01369613,0.6251814,0.2960176],"study_design_scores_gemma":[0.0001772107,0.0002330677,0.02000463,0.000480075,0.0001600957,0.001765128,0.0007425852,0.03939936,0.03722933,0.008827311,0.890723,0.0002581321],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.07785952,0.003006589,0.2524015,0.001451778,0.002208153,0.001692725,0.5728976,0.04618397,0.04229807],"genre_scores_gemma":[0.06207394,0.0006622871,0.2182993,0.0003362275,0.0002311401,0.001281319,0.7059507,0.00229339,0.008871692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008997921,"threshold_uncertainty_score":0.02791625,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2773782067","doi":"","title":"Chat Disentanglement: Identifying Semantic Reply Relationships with Random Forests and Recurrent Neural Networks","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":33,"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; Thread (computing); Random forest; Recurrent neural network; Classifier (UML); Artificial intelligence; Machine learning; Artificial neural network; Natural language processing; Data mining; Programming language","authors":[{"name":"Shikib Mehri","is_ca":false},{"name":"Giuseppe Carenini","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06351610469634573,"gpt":0.3261799200032158,"spread":0.2626638153068701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003155158,0.001503502,0.0009468862,0.002752788,0.0007243079,0.001159694,0.001670173,0.001323856,0.001641202],"category_scores_gemma":[0.008988333,0.0004414877,0.001084341,0.001421497,0.0004702559,0.00229264,0.001247327,0.0022187,0.001566684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005925386,"about_ca_system_score_gemma":0.0009297446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005649163,"about_ca_topic_score_gemma":0.01186592,"domain_scores_codex":[0.9987155,0.0004504313,0.00008588241,0.000409263,0.0001814825,0.0001575541],"domain_scores_gemma":[0.995201,0.002746862,0.0006579058,0.0005203387,0.0006354248,0.0002384384],"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":[0.0009850193,0.001041862,0.03801064,0.0002991072,0.0003162561,0.00049001,0.001373655,0.1247446,0.02222825,0.008482952,0.01237323,0.7896544],"study_design_scores_gemma":[0.00001332752,0.00004492322,0.001656668,0.00001342148,0.00002442117,0.00003675342,0.00008850621,0.9881421,0.002580139,0.006482776,0.0009024745,0.00001453598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1688306,0.0007042571,0.8211468,0.0004794054,0.0001562678,0.0002240039,0.00114413,0.005163367,0.002151193],"genre_scores_gemma":[0.7638399,0.000176022,0.2265305,0.0001431346,0.000175316,0.0002484096,0.003817233,0.0002879011,0.004781576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005649163,"threshold_uncertainty_score":0.01668626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132959801","doi":"","title":"Incremental Segmentation and Decoding Strategies for Simultaneous Translation","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"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; Decoding methods; Segmentation; Artificial intelligence; Machine translation; Speech recognition; Interpreter; Natural language processing; Speech translation; Active listening; Phrase; Task (project management); Latency (audio); Translation (biology); Algorithm; Programming language; Communication","authors":[{"name":"Mahsa Yarmohammadi","is_ca":false},{"name":"Vivek Kumar Rangarajan Sridhar","is_ca":false},{"name":"Srinivas Bangalore","is_ca":false},{"name":"Baskaran Sankaran","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02833968079378524,"gpt":0.3111720211243554,"spread":0.2828323403305702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00118976,0.00154588,0.0007749198,0.0009082578,0.0006734453,0.001715172,0.001598369,0.001723683,0.00477539],"category_scores_gemma":[0.007382683,0.0005481722,0.0007531188,0.001251815,0.0008316542,0.002230992,0.001337794,0.00155192,0.003442335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005516809,"about_ca_system_score_gemma":0.001468561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00271028,"about_ca_topic_score_gemma":0.005075884,"domain_scores_codex":[0.9985215,0.0004960381,0.0001119221,0.0003231731,0.0004087095,0.0001386537],"domain_scores_gemma":[0.9955238,0.002467539,0.0001526054,0.0007412669,0.001000225,0.0001145576],"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":[0.0009165783,0.0001823102,0.001149922,0.0004554378,0.00007999012,0.0004687773,0.001352361,0.03824735,0.1724898,0.01812171,0.003840883,0.7626949],"study_design_scores_gemma":[0.0001429355,0.0005070817,0.001483224,0.00005686787,0.0001889958,0.001391553,0.0005531037,0.6521763,0.3029024,0.02456017,0.0158797,0.000157739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0240944,0.0003484297,0.9680388,0.0001061177,0.00006866621,0.00009135614,0.0001251158,0.003611633,0.003515601],"genre_scores_gemma":[0.2474658,0.0003203956,0.7465414,0.0001426069,0.00006703437,0.0001823087,0.0006952788,0.001048253,0.003536893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00477539,"threshold_uncertainty_score":0.01597524,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2622583534","doi":"","title":"Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging","year":2016,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","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":"University of Lethbridge","funders":"","keywords":"Submodular set function; Automatic summarization; Computer science; Redundancy (engineering); Sentence; Artificial intelligence; Natural language processing; Scalability; Set (abstract data type); Multi-document summarization; Information retrieval; Mathematics; Database","authors":[{"name":"Yllias Chali","is_ca":true},{"name":"Moin Mahmud Tanvee","is_ca":false},{"name":"Mir Tafseer Nayeem","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03583080388495406,"gpt":0.3049195049577958,"spread":0.2690887010728417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002680197,0.002062341,0.002371775,0.003530375,0.000627775,0.001978958,0.001811266,0.001301598,0.001240023],"category_scores_gemma":[0.004376837,0.00044834,0.001515843,0.003200347,0.0006240399,0.002677252,0.001260767,0.001627447,0.001200589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036248,"about_ca_system_score_gemma":0.001238115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002049783,"about_ca_topic_score_gemma":0.002505554,"domain_scores_codex":[0.9982467,0.0006375524,0.0001609466,0.0004191165,0.0004422611,0.00009362699],"domain_scores_gemma":[0.9972814,0.0009212206,0.0004097401,0.0004609509,0.0008192518,0.0001072879],"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":[0.0002439885,0.0002360829,0.0009093006,0.0006925449,0.0002824707,0.0002669059,0.0004923813,0.1379885,0.04512997,0.0131913,0.01154963,0.789017],"study_design_scores_gemma":[0.00003949524,0.000264178,0.0006525848,0.00002834299,0.0001331239,0.0001642328,0.0001033789,0.9543264,0.02013793,0.01681963,0.00728412,0.00004657473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006108075,0.0007268543,0.9904289,0.0001473302,0.00003362759,0.00008182824,0.0002351957,0.001909688,0.0003284587],"genre_scores_gemma":[0.08466768,0.0006608032,0.9096042,0.0002255792,0.0002150083,0.0002842595,0.002395553,0.0002963263,0.001650586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003530375,"threshold_uncertainty_score":0.0141744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963881255","doi":"","title":"Cross-Lingual Sentiment Analysis Without (Good) Translation","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":14,"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":"Computer science; Leverage (statistics); Natural language processing; Sentiment analysis; Artificial intelligence; Machine translation; Word (group theory); Translation (biology); Set (abstract data type); Context (archaeology); Linguistics","authors":[{"name":"Mohamed Abdalla","is_ca":true},{"name":"Graeme Hirst","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04957342895840701,"gpt":0.3699171184644701,"spread":0.3203436895060631,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001864752,0.001139749,0.0008205719,0.001638251,0.0008775954,0.001687212,0.0005685781,0.0004754127,0.006143799],"category_scores_gemma":[0.005393342,0.0003661306,0.001088465,0.001912362,0.0004510423,0.00207573,0.002089122,0.0009883973,0.006243427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004742036,"about_ca_system_score_gemma":0.0009861069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002201918,"about_ca_topic_score_gemma":0.003603062,"domain_scores_codex":[0.9984784,0.00043365,0.0001634168,0.000412986,0.0003505408,0.0001610936],"domain_scores_gemma":[0.9976634,0.0004187384,0.0001923145,0.0007033627,0.0009677391,0.00005452487],"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":[0.0005834466,0.0004098713,0.02175459,0.0005310194,0.0005378021,0.000602242,0.001693659,0.008713324,0.1062135,0.01151283,0.03438369,0.813064],"study_design_scores_gemma":[0.000143916,0.0006152017,0.07065301,0.0001916878,0.0006793252,0.001210071,0.00562917,0.5227062,0.1648809,0.07429024,0.158738,0.0002623136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1809984,0.000747651,0.7798687,0.0007913908,0.0006347573,0.0003283457,0.005655038,0.006170456,0.0248053],"genre_scores_gemma":[0.7200742,0.0004992926,0.2536284,0.0004610705,0.0002077219,0.0005860943,0.01137635,0.001215226,0.01195152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006143799,"threshold_uncertainty_score":0.02055311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2773947245","doi":"","title":"MONPA: Multi-objective Named-entity and Part-of-speech Annotator for Chinese using Recurrent Neural Network","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"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; Natural language processing; Artificial intelligence; Named-entity recognition; Sentence; Recurrent neural network; Task (project management); Segmentation; Speech recognition; Part of speech; Word (group theory); Artificial neural network; Named entity; Text segmentation","authors":[{"name":"Yu Lun Hsieh","is_ca":false},{"name":"Yung‐Chun Chang","is_ca":true},{"name":"Yi Huang","is_ca":false},{"name":"Shu Yeh","is_ca":false},{"name":"Chun‐Hung Chen","is_ca":false},{"name":"Wen Lian Hsu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05657633475324485,"gpt":0.3502884604063141,"spread":0.2937121256530692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002950841,0.002052781,0.001106672,0.001378383,0.001253007,0.001190665,0.002618328,0.001369752,0.004990444],"category_scores_gemma":[0.003889653,0.0007009138,0.001086381,0.001143375,0.0004857301,0.002639902,0.002414027,0.001405382,0.003692521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0013043,"about_ca_system_score_gemma":0.003171538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03145958,"about_ca_topic_score_gemma":0.05863275,"domain_scores_codex":[0.998833,0.000264142,0.00005856735,0.0005419839,0.0001726421,0.0001296114],"domain_scores_gemma":[0.9985983,0.0004584061,0.0001152154,0.0003099674,0.0004280175,0.00009004408],"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":[0.001310694,0.0004065782,0.01004979,0.0008835337,0.0005902103,0.001238052,0.0007919887,0.08983268,0.06468228,0.006075891,0.07937285,0.7447655],"study_design_scores_gemma":[0.00005193913,0.0001021906,0.00197625,0.00002550663,0.00009642576,0.0001293429,0.0001115838,0.9615387,0.02324027,0.003578237,0.009084697,0.00006486975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05895265,0.0008457184,0.8584614,0.0003932603,0.000320028,0.0004528605,0.005649733,0.07050912,0.004415226],"genre_scores_gemma":[0.3342476,0.0004286124,0.6150981,0.0004161798,0.0001103425,0.0009022409,0.02375269,0.002899118,0.02214518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03145958,"threshold_uncertainty_score":0.06255293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2775337853","doi":"","title":"Assessing the Verifiability of Attributions in News Text","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","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":"McGill University","funders":"","keywords":"Operationalization; Attribution; Verifiable secret sharing; Computer science; Rank (graph theory); Task (project management); Fidelity; Crowdsourcing; Statement (logic); Authorship attribution; Natural language processing; Information retrieval; Artificial intelligence; Psychology; Social psychology; World Wide Web; Linguistics; Set (abstract data type); Mathematics","authors":[{"name":"Edward Newell","is_ca":true},{"name":"Ariane Schang","is_ca":false},{"name":"Drew Margolin","is_ca":false},{"name":"Derek Ruths","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0672499933037815,"gpt":0.3678505938284904,"spread":0.3006006005247089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05141924,0.001244263,0.001003442,0.009632406,0.001718577,0.005900906,0.001810962,0.002788925,0.002760623],"category_scores_gemma":[0.3281011,0.0006121808,0.0009330604,0.006311119,0.003203241,0.007972193,0.004017776,0.002493978,0.001327152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153197,"about_ca_system_score_gemma":0.00141307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005097965,"about_ca_topic_score_gemma":0.004438244,"domain_scores_codex":[0.9631476,0.0179947,0.003271255,0.005432263,0.009135879,0.001018359],"domain_scores_gemma":[0.4267029,0.4742189,0.05132763,0.02338464,0.02229226,0.002073616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002722521,0.0009332635,0.5802754,0.002076353,0.001359546,0.001412533,0.0138393,0.04231578,0.02090965,0.01610883,0.00735031,0.3106966],"study_design_scores_gemma":[0.0002259912,0.0008520853,0.4298631,0.0006541682,0.0005838742,0.001263705,0.006238094,0.4427297,0.04363798,0.05936116,0.0139651,0.0006250087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.872023,0.001205446,0.1108798,0.001042589,0.0003173017,0.0003150039,0.002546291,0.0008276884,0.01084291],"genre_scores_gemma":[0.9833265,0.0001359869,0.01430997,0.00005620603,0.0001347221,0.00006744466,0.001334537,0.00006296337,0.0005716559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05141924,"threshold_uncertainty_score":0.2719342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2252242089","doi":"","title":"On the Effectiveness of Using Syntactic and Shallow Semantic Tree Kernels for Automatic Assessment of Essays","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","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":"University of Lethbridge","funders":"","keywords":"Computer science; Natural language processing; Grading (engineering); Artificial intelligence; Latent semantic analysis; Task (project management); Tree (set theory); Tree structure; Data structure; Programming language","authors":[{"name":"Yllias Chali","is_ca":true},{"name":"Sadid A. Hasan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03193183759763282,"gpt":0.3179565227045993,"spread":0.2860246851069665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009898956,0.001201181,0.000956319,0.001847619,0.0008028311,0.002376148,0.00107199,0.002174393,0.001296794],"category_scores_gemma":[0.03698063,0.0004764797,0.0006586504,0.0009928595,0.0008783403,0.006000955,0.002018352,0.00202583,0.00093815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009466435,"about_ca_system_score_gemma":0.001185455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008450241,"about_ca_topic_score_gemma":0.006987072,"domain_scores_codex":[0.9960114,0.002265757,0.0002620561,0.0005722524,0.0006394,0.0002492303],"domain_scores_gemma":[0.961245,0.03061359,0.001155355,0.002345459,0.003991742,0.0006488019],"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":[0.00277779,0.001092327,0.02169447,0.0002353681,0.0003080533,0.0001175511,0.0004993048,0.2030893,0.02212392,0.009571344,0.003492478,0.7349982],"study_design_scores_gemma":[0.00002214118,0.0001117899,0.002216419,0.00001226045,0.00003473412,0.00002318512,0.00005373203,0.9910263,0.003243483,0.003027031,0.0002105977,0.00001819455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6074589,0.002223789,0.3810941,0.001211913,0.0001550656,0.0001192647,0.0002129237,0.002417459,0.00510664],"genre_scores_gemma":[0.9511302,0.0003121138,0.04672012,0.00007921836,0.00004764641,0.00002362081,0.0002821313,0.00007582788,0.001329094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009898956,"threshold_uncertainty_score":0.05235136,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}