{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":13,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":13,"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":"73698f1fbcfb","filters":{"venue":"North American Chapter of the Association for Computational Linguistics"}},"results":[{"id":"W30283642","doi":"10.1002/evl3.9","title":"Hierarchical versus Flat Classification of Emotions in Text","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":69,"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":"Computer science; Task (project management); Polarity (international relations); Artificial intelligence; Neutrality; Hierarchical database model; Machine learning; Pattern recognition (psychology); Data mining; Natural language processing; Engineering","authors":[{"name":"Diman Ghazi","is_ca":true},{"name":"Diana Inkpen","is_ca":true},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02534671414079879,"gpt":0.288668501698871,"spread":0.2633217875580722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007585837,0.000527042,0.0003012099,0.003743437,0.0007221451,0.001947421,0.0005484516,0.0006245879,0.01723337],"category_scores_gemma":[0.007433729,0.00009678444,0.000364991,0.002603496,0.0008373816,0.003708951,0.001215756,0.0006932634,0.004993873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007893389,"about_ca_system_score_gemma":0.0002993674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001963716,"about_ca_topic_score_gemma":0.00253072,"domain_scores_codex":[0.9989645,0.0002561596,0.0001388125,0.0001977502,0.0002932199,0.0001494801],"domain_scores_gemma":[0.9960199,0.002138429,0.0004937918,0.0002678215,0.0007827207,0.0002973305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002994807,0.0003268727,0.08776324,0.00234069,0.0001860131,0.001471619,0.01051101,0.003767943,0.042926,0.03683351,0.09067166,0.7202067],"study_design_scores_gemma":[0.0001335662,0.0007669736,0.4836673,0.001280468,0.0002605065,0.002343067,0.02247305,0.1923442,0.01514428,0.1336935,0.1476559,0.0002371561],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.695809,0.003976427,0.0904965,0.003414454,0.0009040656,0.001350305,0.03494816,0.004255372,0.1648458],"genre_scores_gemma":[0.9561647,0.0004670082,0.02624481,0.0002329485,0.0002592663,0.0003330236,0.009479703,0.0001742246,0.006644187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01723337,"threshold_uncertainty_score":0.0576514,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W17659133","doi":"10.1017/s1481803500004127","title":"Joint Parsing and Alignment with Weakly Synchronized Grammars","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Parsing; Computer science; Natural language processing; Artificial intelligence; Treebank; Word (group theory); Bottom-up parsing; Machine translation; Top-down parsing; Rule-based machine translation; Discriminative model; Speech recognition; Linguistics","authors":[{"name":"David Burkett","is_ca":false},{"name":"John Blitzer","is_ca":false},{"name":"Dan Klein","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007642669732457285,"gpt":0.2343343053735263,"spread":0.226691635641069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003632112,0.001217898,0.001432959,0.002243649,0.002271577,0.004170787,0.002607314,0.001508511,0.008892339],"category_scores_gemma":[0.01150405,0.00156194,0.001766762,0.004040121,0.002384171,0.004769397,0.004125091,0.002368628,0.005176321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002158517,"about_ca_system_score_gemma":0.00739217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0496144,"about_ca_topic_score_gemma":0.08972228,"domain_scores_codex":[0.9963085,0.001595477,0.0002378718,0.0007998294,0.0006823632,0.0003758777],"domain_scores_gemma":[0.9945398,0.00285449,0.000210426,0.001360644,0.0009019992,0.0001326884],"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":[0.0005676992,0.0001377403,0.002499492,0.0005544507,0.0002171506,0.0007376628,0.001636368,0.1090238,0.01383794,0.3323434,0.04474549,0.4936989],"study_design_scores_gemma":[0.00008462347,0.00008375179,0.001450563,0.0001008806,0.0001519568,0.000292674,0.0003645165,0.4979049,0.01839572,0.4346687,0.04637557,0.0001261389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00924834,0.0003511496,0.9699931,0.0004589333,0.0001303857,0.0001004191,0.001110692,0.009720474,0.00888657],"genre_scores_gemma":[0.2009662,0.0006552625,0.7730389,0.0002416966,0.0001520488,0.0001732146,0.006974432,0.004637808,0.01316036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0496144,"threshold_uncertainty_score":0.09865123,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1888011339","doi":"","title":"Clinical Information Retrieval using Document and PICO Structure","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Information retrieval; Weighting; Computer science; Document Structure Description; Data mining; Medicine; XML; World Wide Web","authors":[{"name":"Florian Boudin","is_ca":true},{"name":"Jian‐Yun Nie","is_ca":true},{"name":"Martin Dawes","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01164874062539717,"gpt":0.3002182539384063,"spread":0.2885695133130092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003358747,0.0009640335,0.001797333,0.01639556,0.001132382,0.002932613,0.001073433,0.001335185,0.002612438],"category_scores_gemma":[0.02494479,0.0006201572,0.001441727,0.01232926,0.0008873081,0.007831783,0.002873014,0.001043484,0.0016898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001784869,"about_ca_system_score_gemma":0.002258616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004895874,"about_ca_topic_score_gemma":0.004865097,"domain_scores_codex":[0.9957455,0.001359225,0.0006999595,0.0007853025,0.0012529,0.0001571201],"domain_scores_gemma":[0.9880932,0.007001623,0.001326407,0.001423159,0.001821496,0.0003340661],"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":[0.001067427,0.0003384002,0.01199412,0.001561504,0.0003679744,0.0004783221,0.001372703,0.028672,0.01812079,0.03614822,0.02262082,0.8772578],"study_design_scores_gemma":[0.0003627515,0.0009802581,0.01262307,0.0004379514,0.0005461806,0.00198758,0.00101213,0.7502884,0.01876292,0.1506119,0.06213248,0.0002543067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09959158,0.008047386,0.8651266,0.002597828,0.0004259,0.001113474,0.008850271,0.006350489,0.007896395],"genre_scores_gemma":[0.4315706,0.002981223,0.5437069,0.0006110973,0.0006779201,0.001177987,0.01450524,0.0004238821,0.004345237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01639556,"threshold_uncertainty_score":0.01776296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2912796987","doi":"","title":"Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature","year":2012,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Computational linguistics; Linguistics; Natural language processing; Philosophy","authors":[{"name":"David K. Elson","is_ca":false},{"name":"Anna Kazantseva","is_ca":true},{"name":"Rada Mihalcea","is_ca":false},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01366432469359548,"gpt":0.2764200507866348,"spread":0.2627557260930394,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01354791,0.001454835,0.002865105,0.005133531,0.004271756,0.01712621,0.003038378,0.00263616,0.04357855],"category_scores_gemma":[0.02383636,0.001402715,0.001747259,0.00366646,0.002771959,0.01856036,0.01110659,0.007866414,0.02091456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003540784,"about_ca_system_score_gemma":0.007946497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006851045,"about_ca_topic_score_gemma":0.01911126,"domain_scores_codex":[0.9917237,0.00498149,0.0007596897,0.001093778,0.001114739,0.0003265808],"domain_scores_gemma":[0.9793103,0.009439401,0.0004965748,0.003448745,0.004826242,0.002478644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002834231,0.0003756409,0.0008579878,0.0008044255,0.00009137725,0.0002551888,0.00279703,0.000459633,0.002861226,0.03666759,0.8084598,0.1460866],"study_design_scores_gemma":[0.00007788162,0.00002884175,0.0008468859,0.0005638821,0.0000752777,0.0002777825,0.001595226,0.003305534,0.001874553,0.04433934,0.9469571,0.00005782683],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.02832275,0.05597597,0.4548256,0.1770395,0.06921454,0.002011116,0.02936782,0.01572698,0.1675158],"genre_scores_gemma":[0.1237879,0.03218349,0.3560477,0.01845821,0.01970271,0.002128405,0.1560612,0.01033293,0.2812975],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.04357855,"threshold_uncertainty_score":0.1457848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138392784","doi":"","title":"Using the Omega Index for Evaluating Abstractive Community Detection","year":2012,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":26,"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; University of the Fraser Valley","funders":"","keywords":"Automatic summarization; Computer science; Disjoint sets; Sentence; Artificial intelligence; Natural language processing; Cluster analysis; Metric (unit); Graph; Contrast (vision); Task (project management); Index (typography); Theoretical computer science; Mathematics; Combinatorics","authors":[{"name":"Gabriel Murray","is_ca":true},{"name":"Giuseppe Carenini","is_ca":true},{"name":"Raymond T. Ng","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06175701061134741,"gpt":0.3600102047298923,"spread":0.2982531941185449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01915702,0.001784933,0.002026872,0.02034183,0.001919785,0.00372228,0.001991427,0.002832119,0.001743963],"category_scores_gemma":[0.08971703,0.000387611,0.001291091,0.009459052,0.001490909,0.007916667,0.002977448,0.001647332,0.0008260077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001778961,"about_ca_system_score_gemma":0.001113117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00231731,"about_ca_topic_score_gemma":0.003075038,"domain_scores_codex":[0.9827949,0.00554882,0.002259723,0.001781642,0.007151089,0.0004637661],"domain_scores_gemma":[0.9050149,0.06912187,0.007401139,0.00479085,0.01200143,0.001669834],"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":[0.001990613,0.0008835216,0.09209146,0.001942504,0.001803459,0.0003109456,0.001844221,0.127092,0.02315664,0.01991594,0.01761166,0.7113569],"study_design_scores_gemma":[0.0001805092,0.001853562,0.03470733,0.0001835903,0.0003831762,0.0005691363,0.001263175,0.8826395,0.03630363,0.0324649,0.009229485,0.0002220079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3274742,0.002780998,0.6474901,0.0006891683,0.0004095432,0.00088879,0.003175659,0.003518865,0.01357272],"genre_scores_gemma":[0.5487449,0.0006240808,0.4417689,0.0001382391,0.0001439685,0.0005757093,0.006019797,0.0004579815,0.001526438],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02034183,"threshold_uncertainty_score":0.1013132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792194291","doi":"","title":"Multi-way classification of semantic relations between pairs of nominals","year":2009,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Information retrieval; Philosophy","authors":[{"name":"Iris Hendrickx","is_ca":false},{"name":"Su Nam Kim","is_ca":false},{"name":"Zornitsa Kozareva","is_ca":false},{"name":"Preslav Nakov","is_ca":false},{"name":"Diarmuid Ã“ SÃ©aghdha","is_ca":false},{"name":"Sebastian PadÃ","is_ca":false},{"name":"Marco Pennacchiotti","is_ca":false},{"name":"Lorenza Romano","is_ca":false},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02596209898882572,"gpt":0.29546025094887,"spread":0.2694981519600443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001758135,0.0005201155,0.0005517682,0.005344762,0.00163048,0.002624678,0.001006853,0.001203629,0.006085287],"category_scores_gemma":[0.007031174,0.0002378225,0.001344668,0.002873498,0.0009417874,0.005089556,0.002098062,0.00124844,0.002186568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008489018,"about_ca_system_score_gemma":0.001083127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002103192,"about_ca_topic_score_gemma":0.003911016,"domain_scores_codex":[0.9979677,0.0004602422,0.0002875823,0.0005894295,0.0004979071,0.000197278],"domain_scores_gemma":[0.9942849,0.002488459,0.0006464713,0.0007958736,0.001400126,0.0003840893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004125077,0.000642302,0.1368768,0.001236019,0.0004089263,0.001279859,0.004361672,0.003972313,0.08478189,0.05960399,0.01590038,0.6868107],"study_design_scores_gemma":[0.0002208724,0.001165785,0.2331066,0.0009351146,0.001034435,0.004003925,0.01715405,0.3168921,0.06904742,0.2690659,0.08701351,0.0003604827],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7173652,0.002325051,0.241105,0.001283687,0.0006565924,0.0003618425,0.009777943,0.002587453,0.0245372],"genre_scores_gemma":[0.8806752,0.0003311092,0.1062011,0.00007508048,0.00008133153,0.0001422862,0.008176471,0.0001445654,0.00417287],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006085287,"threshold_uncertainty_score":0.02035725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2251261672","doi":"","title":"Extracting Information for Generating A Diabetes Report Card from Free Text in Physicians Notes","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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; McMaster University; University of Ottawa","funders":"","keywords":"Text messaging; Computer science; Guideline; Diabetes mellitus; Population; Health records; Process (computing); Information retrieval; Medicine; Data mining; World Wide Web","authors":[{"name":"Ramanjot Singh Bhatia","is_ca":true},{"name":"Amber Graystone","is_ca":true},{"name":"Ross A. Davies","is_ca":true},{"name":"Susan McClinton","is_ca":true},{"name":"Jason Morín","is_ca":true},{"name":"Richard F. Davies","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009028242911674093,"gpt":0.255037806892002,"spread":0.2460095639803279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002304493,0.001227641,0.0008690779,0.007183807,0.000759609,0.002082554,0.001065245,0.001445944,0.004174344],"category_scores_gemma":[0.01456205,0.0004759866,0.001112517,0.004019812,0.0003686568,0.002370662,0.001226439,0.001037991,0.005987637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000937253,"about_ca_system_score_gemma":0.002635707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004792041,"about_ca_topic_score_gemma":0.005333318,"domain_scores_codex":[0.9978912,0.0004341774,0.0004339948,0.0004832161,0.0006474072,0.0001100162],"domain_scores_gemma":[0.9882108,0.007699793,0.001078569,0.001077332,0.00171291,0.0002206735],"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":[0.0008222708,0.0008147187,0.02563092,0.001627513,0.0001530775,0.001675945,0.001194037,0.008630565,0.02751597,0.003515142,0.06753212,0.8608877],"study_design_scores_gemma":[0.0006826077,0.0008276475,0.07426293,0.001286065,0.0007267353,0.003914998,0.005810649,0.4258437,0.2095212,0.02796996,0.2487402,0.0004132986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1966885,0.001734246,0.5746117,0.00369848,0.0007117746,0.004604413,0.1660511,0.04265761,0.009242099],"genre_scores_gemma":[0.1193177,0.0007510384,0.7279277,0.000367234,0.0001816077,0.001056766,0.1474644,0.0004311066,0.002502471],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007183807,"threshold_uncertainty_score":0.01396459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1548457881","doi":"","title":"Communication strategies for a computerized caregiver for individuals with Alzheimerâ€™s disease","year":2012,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Speech and dialogue systems","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 Ottawa; University of Toronto","funders":"","keywords":"Task (project management); Vocabulary; Computer science; Preprocessor; Confusion; Disease; Noise (video); Human–computer interaction; Speech recognition; Cognitive psychology; Artificial intelligence; Natural language processing; Machine learning; Psychology; Medicine; Linguistics","authors":[{"name":"Frank Rudzicz","is_ca":true},{"name":"Rozanne Wilson","is_ca":true},{"name":"Alex Mihailidis","is_ca":true},{"name":"Elizabeth Rochon","is_ca":true},{"name":"Carol Léonard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02078250978325165,"gpt":0.2659044236375044,"spread":0.2451219138542528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001096269,0.0008742235,0.0002777631,0.0005016558,0.001227903,0.001052771,0.0007139011,0.0008345641,0.008433843],"category_scores_gemma":[0.005153134,0.0002036762,0.0003689011,0.0001846787,0.0004461801,0.001177844,0.0009684137,0.0004556105,0.003004386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003463926,"about_ca_system_score_gemma":0.0007740699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001362012,"about_ca_topic_score_gemma":0.002717564,"domain_scores_codex":[0.9995165,0.0002889817,0.00003669245,0.00007756297,0.00004512121,0.00003506397],"domain_scores_gemma":[0.9989583,0.0005282649,0.00009733599,0.0001306637,0.0001980899,0.00008733641],"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":[0.0006247422,0.0009324775,0.04598789,0.0005418925,0.00005354832,0.00683798,0.03849151,0.002964701,0.04191914,0.01024564,0.04904838,0.8023522],"study_design_scores_gemma":[0.0008307477,0.003379811,0.09296969,0.001688323,0.0007879833,0.04103044,0.1454454,0.1621914,0.1124658,0.07832266,0.3600138,0.000873939],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7176696,0.001653309,0.2230652,0.008952122,0.000393257,0.0009139349,0.0006402456,0.006963903,0.0397485],"genre_scores_gemma":[0.8126693,0.0005618527,0.1714414,0.0008371808,0.0000740673,0.0002588595,0.0004626174,0.0002228584,0.01347185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008433843,"threshold_uncertainty_score":0.02821404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W99763915","doi":"","title":"Search Engine Adaptation by Feedback Control Adjustment for Time-sensitive Query","year":2009,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Adaptation (eye); Search engine; Control (management); Information retrieval; Artificial intelligence; Psychology","authors":[{"name":"Ruiqiang Zhang","is_ca":false},{"name":"Yi Chang","is_ca":false},{"name":"Zhaohui Zheng","is_ca":false},{"name":"Donald Metzler","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01031049870942268,"gpt":0.239400819674497,"spread":0.2290903209650743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002020433,0.0009272467,0.001330773,0.001113637,0.0005346052,0.001245438,0.00185523,0.001119477,0.003442289],"category_scores_gemma":[0.01386401,0.0004059285,0.0004914049,0.001026512,0.0004614559,0.00183312,0.0009396269,0.001266063,0.001030948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006733516,"about_ca_system_score_gemma":0.00119309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007757016,"about_ca_topic_score_gemma":0.005981847,"domain_scores_codex":[0.9984547,0.0002784067,0.0001196818,0.0004846414,0.0004687356,0.0001938124],"domain_scores_gemma":[0.9959773,0.001729396,0.0002209586,0.0006216256,0.001293801,0.0001569054],"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":[0.001872526,0.00133821,0.004912453,0.0002974466,0.0001993678,0.0002527951,0.0003920967,0.07376473,0.1247603,0.003141904,0.01259445,0.7764737],"study_design_scores_gemma":[0.00009577196,0.0001929872,0.002406419,0.000008428331,0.00008857375,0.0001107706,0.0000584281,0.9669119,0.02640233,0.0016809,0.002000071,0.00004357165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.172706,0.001761155,0.7998976,0.0005715367,0.0006526272,0.0004016266,0.0003117422,0.01899933,0.004698484],"genre_scores_gemma":[0.9251812,0.000152708,0.07098637,0.0002116561,0.0001425703,0.0001016451,0.0002753414,0.0004003635,0.002548281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007757016,"threshold_uncertainty_score":0.01542372,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151069987","doi":"","title":"Automatic Answer Typing for How-Questions","year":2007,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","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 Alberta","funders":"","keywords":"Typing; Computer science; Information retrieval; Natural language processing; World Wide Web; Artificial intelligence; Speech recognition","authors":[{"name":"Christopher Pinchak","is_ca":true},{"name":"Shane Bergsma","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01887462943214532,"gpt":0.273063253563209,"spread":0.2541886241310637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005379912,0.001733506,0.002543032,0.006045084,0.001345254,0.003895574,0.00217224,0.001965271,0.009997705],"category_scores_gemma":[0.04123107,0.001113169,0.001486826,0.003236426,0.0009100765,0.007411645,0.00468862,0.002764301,0.007164274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007323854,"about_ca_system_score_gemma":0.001677191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002288708,"about_ca_topic_score_gemma":0.003770864,"domain_scores_codex":[0.990907,0.002705568,0.001017477,0.00245628,0.002358157,0.0005555619],"domain_scores_gemma":[0.9592229,0.02327768,0.002574212,0.006744175,0.007175687,0.001005412],"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":[0.0006932762,0.0005919515,0.03720462,0.001817213,0.0002540986,0.0004892935,0.006998597,0.002434586,0.05940899,0.02934752,0.05858085,0.802179],"study_design_scores_gemma":[0.000242486,0.0004697434,0.03742491,0.0007297228,0.0003383976,0.002020672,0.005355587,0.3838231,0.169765,0.1531832,0.2461233,0.0005239127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04636135,0.0004771262,0.8867611,0.0007287882,0.0002887681,0.0008169408,0.00785917,0.05223504,0.004471771],"genre_scores_gemma":[0.2396369,0.0002981451,0.7128103,0.0005368505,0.0002962639,0.001169139,0.03102696,0.006025112,0.008200328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009997705,"threshold_uncertainty_score":0.0334456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1714170610","doi":"","title":"Grammaticality Judgement in a Word Completion Task","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Speech and dialogue systems","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":"Holland Bloorview Kids Rehabilitation Hospital","funders":"","keywords":"Computer science; Grammaticality; Natural language processing; Syntax; Word (group theory); Judgement; Task (project management); Artificial intelligence; Usability; Grammar; Linguistics; Human–computer interaction","authors":[{"name":"Alfred I. Renaud","is_ca":false},{"name":"Fraser Shein","is_ca":true},{"name":"Vivian Tsang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01283611387327251,"gpt":0.2508910349973942,"spread":0.2380549211241217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01274541,0.001105394,0.0008467242,0.001259983,0.0008114777,0.002587668,0.001169778,0.001845645,0.005525734],"category_scores_gemma":[0.1578413,0.0004312453,0.0005144214,0.0006606511,0.001394525,0.004283687,0.001847449,0.001226599,0.001782836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005970861,"about_ca_system_score_gemma":0.0006667801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001783194,"about_ca_topic_score_gemma":0.001278364,"domain_scores_codex":[0.9870432,0.00681073,0.0007986624,0.002244439,0.002649584,0.0004533188],"domain_scores_gemma":[0.8594905,0.1138348,0.007182461,0.006088895,0.01170926,0.001694052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.005830944,0.001467648,0.05185877,0.002665985,0.0002719062,0.001399967,0.08604246,0.0071014,0.5108795,0.004433314,0.007390241,0.3206578],"study_design_scores_gemma":[0.001370089,0.01704944,0.5220127,0.001123095,0.000618014,0.0060102,0.03473538,0.1216966,0.2054669,0.03901651,0.04906343,0.001837601],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9473209,0.000252073,0.03981339,0.0001741486,0.0001188325,0.0005500945,0.000222705,0.0006553204,0.01089266],"genre_scores_gemma":[0.9675627,0.0001081092,0.02829005,0.0002671956,0.0000633556,0.0003266263,0.0005551292,0.0003462959,0.002480606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01274541,"threshold_uncertainty_score":0.06740499,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W30536900","doi":"10.1111/risa.13248","title":"Data-driven computational linguistics at FaMAF-UNC, Argentina","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computational linguistics; Computer science; Applied linguistics; Linguistics; Language technology; Language and Communication Technologies; Natural language; Natural language processing; Data science; Philosophy","authors":[{"name":"Laura Alonso Alemany","is_ca":false},{"name":"Gabriel Infante-López","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02033526140629643,"gpt":0.2892357441993217,"spread":0.2689004827930253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005189016,0.0006734183,0.000867941,0.002276249,0.002668364,0.005137356,0.0008463688,0.001460109,0.02301349],"category_scores_gemma":[0.01593109,0.0005345237,0.0007315933,0.003562878,0.001688116,0.002110455,0.002357335,0.001391202,0.007413831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006513893,"about_ca_system_score_gemma":0.007582611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05579071,"about_ca_topic_score_gemma":0.04460387,"domain_scores_codex":[0.9948338,0.002825684,0.0002480086,0.001075806,0.0007909596,0.0002257124],"domain_scores_gemma":[0.9887129,0.00753114,0.000402211,0.0009191437,0.001954317,0.0004803114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006248598,0.0002538172,0.01824433,0.001504099,0.0001387649,0.001310911,0.007436552,0.01163536,0.002984931,0.2166025,0.3505337,0.3887302],"study_design_scores_gemma":[0.00006935431,0.00004081596,0.01205368,0.0009571611,0.00002783921,0.0003126755,0.001885404,0.02627221,0.001780317,0.07823578,0.8783075,0.00005727051],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.1531463,0.04691526,0.235082,0.09323102,0.004262451,0.0008120768,0.08538916,0.01781783,0.3633438],"genre_scores_gemma":[0.5287258,0.01947712,0.2302301,0.002163083,0.001068942,0.00145099,0.06065141,0.007401015,0.1488316],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.05579071,"threshold_uncertainty_score":0.110932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113376122","doi":"","title":"Analysis of Summarization Evaluation Experiments","year":2007,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","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":"Université Laval","funders":"","keywords":"Automatic summarization; Computer science; Terminology; Presentation (obstetrics); Information retrieval; Focus (optics); Natural language processing; Multi-document summarization; Artificial intelligence; Data mining; Linguistics","authors":[{"name":"Marie-Josée Goulet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01988773488424193,"gpt":0.3238424057267155,"spread":0.3039546708424736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06178143,0.001932587,0.001989486,0.004615422,0.001431557,0.002841177,0.001310339,0.001309015,0.00323246],"category_scores_gemma":[0.3287203,0.0005187626,0.001340213,0.004538119,0.00113637,0.003153387,0.001631688,0.001836597,0.001081524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002336572,"about_ca_system_score_gemma":0.001320842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008541035,"about_ca_topic_score_gemma":0.0007710963,"domain_scores_codex":[0.8534503,0.09847936,0.0158567,0.005768466,0.02467674,0.001768533],"domain_scores_gemma":[0.4434772,0.4412593,0.02582361,0.02193425,0.06543244,0.002073239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.03346079,0.00812998,0.07484902,0.01575957,0.005518123,0.0007873436,0.01067213,0.03390468,0.08933765,0.009160733,0.04247938,0.6759406],"study_design_scores_gemma":[0.004653532,0.05362681,0.4646313,0.003656033,0.007907915,0.001699622,0.01037872,0.1222071,0.2367916,0.01900806,0.07400209,0.001437239],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9035753,0.005548877,0.05841694,0.001237951,0.0007223284,0.005571595,0.008591801,0.002683952,0.01365132],"genre_scores_gemma":[0.9487934,0.0007594679,0.03164917,0.0004049794,0.0002234583,0.005344893,0.009149862,0.000791805,0.002882986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06178143,"threshold_uncertainty_score":0.3267354,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}