{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":31,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":31,"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":"2026479010f0","filters":{"venue":"Natural Language Engineering"}},"results":[{"id":"W2126034021","doi":"10.1017/s1351324901002765","title":"Discovery of inference rules for question-answering","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":532,"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":"Question answering; Inference; Computer science; Dependency (UML); Set (abstract data type); Parsing; Artificial intelligence; Natural language processing; Rule of inference; Programming language","authors":[{"name":"Dekang Lin","is_ca":true},{"name":"Patrick Pantel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00715054306742324,"gpt":0.2517287714730841,"spread":0.2445782284056608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01285425,0.001676511,0.001928733,0.007963133,0.002171141,0.003862006,0.004943471,0.00287621,0.004924751],"category_scores_gemma":[0.08408172,0.00161744,0.00342029,0.003867732,0.002223716,0.009593174,0.003825296,0.004992203,0.003836379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001631844,"about_ca_system_score_gemma":0.00260738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003865298,"about_ca_topic_score_gemma":0.00538563,"domain_scores_codex":[0.9877671,0.004144249,0.001487827,0.003281333,0.002952466,0.0003670568],"domain_scores_gemma":[0.9239963,0.06099043,0.002626938,0.006629165,0.005140124,0.0006169625],"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":[0.0002953379,0.0006702197,0.01407066,0.001270908,0.0004968832,0.001019094,0.0034076,0.02648856,0.01118162,0.1192391,0.0280059,0.7938541],"study_design_scores_gemma":[0.00008116165,0.00005574021,0.002439339,0.0002422722,0.0002205779,0.0006252131,0.0005403052,0.5626093,0.01483298,0.3893543,0.02891343,0.00008537435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006798803,0.0003653209,0.9827832,0.000800819,0.00005199747,0.0003577637,0.0009942934,0.006214378,0.001633365],"genre_scores_gemma":[0.05577256,0.0003113596,0.9375631,0.0003386975,0.0001213919,0.0003748164,0.004171626,0.000391837,0.0009544628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01285425,"threshold_uncertainty_score":0.06798059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148362501","doi":"10.1017/s1351324904003560","title":"Correcting real-word spelling errors by restoring lexical cohesion","year":2005,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":180,"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":"Spelling; Computer science; Cohesion (chemistry); Natural language processing; Lexicon; Artificial intelligence; Word (group theory); Context (archaeology); Precision and recall; Recall; Speech recognition; Linguistics","authors":[{"name":"Graeme Hirst","is_ca":true},{"name":"Alexander Budanitsky","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005958882391220053,"gpt":0.2512037126170917,"spread":0.2452448302258716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184212,0.00106736,0.001314397,0.003202153,0.0008274391,0.001460037,0.001177863,0.0009905815,0.001872053],"category_scores_gemma":[0.02004284,0.0004655307,0.0005842037,0.002145015,0.0008340934,0.002031855,0.001683447,0.0009360054,0.002065675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004020141,"about_ca_system_score_gemma":0.00134869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002295416,"about_ca_topic_score_gemma":0.003877066,"domain_scores_codex":[0.9976606,0.0003889921,0.000352266,0.0006811218,0.0007934201,0.0001235423],"domain_scores_gemma":[0.9816126,0.004229346,0.003581859,0.006255423,0.004041274,0.0002794037],"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":[0.0003397275,0.0003096765,0.01995013,0.0007794987,0.0001545116,0.0008543896,0.001380504,0.008452491,0.1991465,0.002169999,0.005659628,0.760803],"study_design_scores_gemma":[0.0003143809,0.0009583621,0.06800993,0.0002633576,0.0007602337,0.005461934,0.001668554,0.1668825,0.6866637,0.01878779,0.04979327,0.0004359946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5211197,0.001364591,0.4521361,0.0006001048,0.0004623499,0.0003287003,0.0009890244,0.01849686,0.004502581],"genre_scores_gemma":[0.611146,0.0004590046,0.3816438,0.0001886218,0.0001155009,0.0001112508,0.001559478,0.0011624,0.003613996],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003202153,"threshold_uncertainty_score":0.0097422,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101481293","doi":"10.1017/s1351324905003694","title":"Segmenting documents by stylistic character","year":2005,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Character (mathematics); Bigram; Natural language processing; Artificial intelligence; Vocabulary; Baseline (sea); Artificial neural network; Market segmentation; Information retrieval; Linguistics; Trigram","authors":[{"name":"N. L. Graham","is_ca":true},{"name":"Graeme Hirst","is_ca":true},{"name":"Bhaskara Marthi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.002330387928883056,"gpt":0.2230677074953706,"spread":0.2207373195664875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006575753,0.0007604807,0.0004301997,0.002581624,0.0005923781,0.001471111,0.0004751205,0.000698226,0.002570204],"category_scores_gemma":[0.004925962,0.0002410243,0.0003354486,0.001896269,0.0002685412,0.001561351,0.0004019001,0.0007431085,0.001841468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000708891,"about_ca_system_score_gemma":0.000600246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004763832,"about_ca_topic_score_gemma":0.008074566,"domain_scores_codex":[0.9994214,0.0001149906,0.00007405524,0.0002213641,0.000100911,0.00006726697],"domain_scores_gemma":[0.996298,0.001767239,0.0004156074,0.000437721,0.0009425578,0.000138972],"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":[0.001466354,0.0002434964,0.01975631,0.0005982485,0.00007541082,0.0005413112,0.00153913,0.01635694,0.152198,0.002612825,0.007200539,0.7974115],"study_design_scores_gemma":[0.0001509193,0.0005785497,0.03348251,0.0001342091,0.0001546173,0.001179779,0.002601127,0.6907223,0.2141464,0.01317678,0.04353256,0.0001403252],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8049209,0.001403977,0.1743625,0.000438691,0.0002283326,0.0006644359,0.004186722,0.005508958,0.008285484],"genre_scores_gemma":[0.7506734,0.0004629633,0.2357334,0.00006779058,0.00007567023,0.0001248842,0.006895785,0.0003061641,0.005659995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004763832,"threshold_uncertainty_score":0.009472251,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029070039","doi":"10.1017/s135132490600444x","title":"A general feature space for automatic verb classification","year":2006,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Lexicon; Artificial intelligence; Feature vector; Natural language processing; Feature (linguistics); Redundancy (engineering); Verb; Support vector machine; Variety (cybernetics); Feature selection; Machine learning; Linguistics","authors":[{"name":"Eric Joanis","is_ca":true},{"name":"Suzanne Stevenson","is_ca":true},{"name":"David A. James","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004724068616820104,"gpt":0.235974427016896,"spread":0.2312503584000759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00186481,0.0009028724,0.001000724,0.001839954,0.0004535997,0.001213617,0.00112357,0.0009818068,0.003043582],"category_scores_gemma":[0.00506897,0.0003023594,0.0009573692,0.001673197,0.0006294756,0.001963662,0.001107494,0.001015136,0.001009899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006458829,"about_ca_system_score_gemma":0.0007808309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002109104,"about_ca_topic_score_gemma":0.00124882,"domain_scores_codex":[0.9987551,0.0004867452,0.0001146068,0.0002428385,0.0002976132,0.0001030592],"domain_scores_gemma":[0.9972331,0.001576872,0.0001660224,0.0003427032,0.000616604,0.00006459888],"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":[0.0005501439,0.0003049586,0.002765108,0.0002059519,0.00008313221,0.0001271795,0.00009866509,0.1085538,0.0203409,0.009618376,0.007277318,0.8500745],"study_design_scores_gemma":[0.0000258956,0.0001097224,0.0008984255,0.00001965319,0.00001341845,0.00006353913,0.00002968744,0.9826207,0.005804028,0.008624844,0.001771175,0.00001903867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04436964,0.0002785197,0.9502981,0.0001697482,0.00003757205,0.0001048887,0.000541235,0.003601626,0.0005986071],"genre_scores_gemma":[0.5600121,0.0001498052,0.4358386,0.0001014182,0.00005618458,0.000434372,0.002077659,0.0001735699,0.00115623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003043582,"threshold_uncertainty_score":0.01018184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044693911","doi":"10.1017/s1351324920000509","title":"Comparison of rule-based and neural network models for negation detection in radiology reports","year":2020,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Population and Public Health","funders":"Engineering and Physical Sciences Research Council; Medical Research Council","keywords":"Computer science; Artificial intelligence; Natural language processing; Negation; Artificial neural network; Sentence; Syntax; Pipeline (software); Machine learning; Rule-based system; Python (programming language); Information retrieval; Programming language","authors":[{"name":"David Sykes","is_ca":false},{"name":"Andreas Grivas","is_ca":false},{"name":"Claire Grover","is_ca":false},{"name":"Richard Tobin","is_ca":false},{"name":"Cathie Sudlow","is_ca":true},{"name":"William Whiteley","is_ca":false},{"name":"Andrew M. McIntosh","is_ca":false},{"name":"Heather C. Whalley","is_ca":false},{"name":"Beatrice Alex","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01456388340755196,"gpt":0.2477711294140073,"spread":0.2332072460064553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004678042,0.001241669,0.001050444,0.001680435,0.000432223,0.001919122,0.002385672,0.001526121,0.002701021],"category_scores_gemma":[0.01546065,0.0005410477,0.001146933,0.0008393092,0.0004920559,0.002279057,0.0007918771,0.001739998,0.0009059091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001872807,"about_ca_system_score_gemma":0.001276108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01860396,"about_ca_topic_score_gemma":0.01347451,"domain_scores_codex":[0.9989027,0.0003664306,0.0001167951,0.0003058289,0.000228522,0.00007973779],"domain_scores_gemma":[0.9859061,0.01160539,0.0005852488,0.0003128485,0.001416443,0.0001738292],"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":[0.0009978489,0.0004443351,0.009266322,0.0002693133,0.000319362,0.0002335095,0.0001175401,0.8407938,0.001475573,0.002024271,0.003461715,0.1405964],"study_design_scores_gemma":[0.000009984504,0.00002563378,0.0002708659,0.00001236861,0.00001678563,0.00001125104,0.000005782727,0.998372,0.000288051,0.0008799936,0.0001022653,0.000005049068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5326376,0.005849206,0.4356994,0.003608453,0.0005726587,0.0005153365,0.003419221,0.007725965,0.009972169],"genre_scores_gemma":[0.910329,0.0006360064,0.08349852,0.0005368945,0.000119071,0.0001725368,0.002454783,0.0001228051,0.002130312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01860396,"threshold_uncertainty_score":0.0369913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137926008","doi":"10.1017/s1351324905004043","title":"Can syllabification improve pronunciation by analogy of English?","year":2006,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","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":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Syllabification; Pronunciation; Computer science; Syllable; Natural language processing; Analogy; Artificial intelligence; Speech recognition; Word (group theory); Linguistics","authors":[{"name":"Yannick Marchand","is_ca":true},{"name":"R.I. Damper","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.001625339182507167,"gpt":0.1923652781234644,"spread":0.1907399389409572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002164605,0.0007957246,0.0008982863,0.000852109,0.000613013,0.00150832,0.001291255,0.001068291,0.0037043],"category_scores_gemma":[0.01850425,0.0004068301,0.0008585754,0.000746957,0.0005670037,0.005124026,0.001441752,0.001487485,0.002023435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006061392,"about_ca_system_score_gemma":0.001031178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003474976,"about_ca_topic_score_gemma":0.004037096,"domain_scores_codex":[0.9985068,0.000689214,0.00007182569,0.0004634197,0.0001755374,0.00009319487],"domain_scores_gemma":[0.9940608,0.00391124,0.0002764971,0.001030195,0.0005707787,0.0001504455],"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":[0.0007694302,0.0002838886,0.01953482,0.0002902073,0.0001330589,0.0002461776,0.0009810155,0.0212546,0.03256743,0.01672924,0.002895321,0.9043148],"study_design_scores_gemma":[0.0001562367,0.001051383,0.02317192,0.0001496012,0.0002851152,0.001112372,0.0009986419,0.7651165,0.06237863,0.1202098,0.02514736,0.0002224691],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3975843,0.003257126,0.5695746,0.002598728,0.0006990565,0.000146574,0.0003363114,0.00718846,0.01861492],"genre_scores_gemma":[0.8140182,0.0005376015,0.1819825,0.000415823,0.0001037757,0.00004974882,0.0003608459,0.0002489116,0.002282654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0037043,"threshold_uncertainty_score":0.01239216,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128424286","doi":"10.1017/s1351324911000167","title":"Query-focused multi-document summarization: automatic data annotations and supervised learning approaches","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automatic summarization; Artificial intelligence; Conditional random field; Semi-supervised learning; Supervised learning; Support vector machine; Annotation; Machine learning; Information retrieval; Natural language processing; Artificial neural network","authors":[{"name":"Yllias Chali","is_ca":true},{"name":"Sadid A. Hasan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05869544911709373,"gpt":0.2372541145684448,"spread":0.178558665451351,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005368747,0.001290555,0.001335166,0.003331459,0.0008739584,0.001219368,0.001670609,0.001154359,0.0007106849],"category_scores_gemma":[0.01506733,0.0004132582,0.0009309745,0.002231134,0.0005904681,0.002876069,0.001058963,0.001357805,0.0007266281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007236545,"about_ca_system_score_gemma":0.0009036917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002113224,"about_ca_topic_score_gemma":0.00432883,"domain_scores_codex":[0.9946114,0.003017387,0.0003786155,0.0009843139,0.0008850521,0.0001232146],"domain_scores_gemma":[0.9788084,0.01188999,0.002240548,0.00278725,0.003968779,0.0003050515],"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":[0.0005805876,0.0007312857,0.003884082,0.0006151026,0.0003202702,0.0001234066,0.0006235235,0.07474454,0.02671475,0.002154268,0.004666821,0.8848415],"study_design_scores_gemma":[0.00006551621,0.0003450304,0.00308276,0.00005620153,0.0001654758,0.0001134344,0.0002058462,0.9503317,0.03599632,0.006081382,0.003491947,0.00006445294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0459548,0.001215327,0.9453755,0.0003531661,0.00006171583,0.0002056337,0.0003159566,0.005723358,0.0007945647],"genre_scores_gemma":[0.2847112,0.0004264672,0.7108411,0.0001530488,0.0001875658,0.000264697,0.001936125,0.0003060896,0.001173834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005368747,"threshold_uncertainty_score":0.02839303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390789641","doi":"10.1017/s1351324923000542","title":"Lightweight transformers for clinical natural language processing","year":2024,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"NIHR Imperial Biomedical Research Centre; Instituto de Salud Carlos III; Medical Research Council; National Institutes of Health; Kementerian Kesihatan Malaysia; All-India Institute of Medical Sciences; Horizon 2020 Framework Programme; Prince Charles Hospital Foundation; Foreign, Commonwealth and Development Office; National Institute for Health Research Health Protection Research Unit; University of Oxford; Norges Forskningsråd; Imperial College London; Conselho Nacional de Desenvolvimento Científico e Tecnológico; University of Cape Town; Public Health England; Wellcome Trust; University College Dublin; Sunnybrook Research Institute; Institut National de la Santé et de la Recherche Médicale; Canadian Institutes of Health Research; National Institute for Health and Care Research; Ministero della Salute; European Federation of Pharmaceutical Industries and Associations; European Commission; Bill and Melinda Gates Foundation","keywords":"Computer science; Transformer; Natural language processing; Artificial intelligence; Electrical engineering","authors":[{"name":"Omid Rohanian","is_ca":false},{"name":"Mohammadmahdi Nouriborji","is_ca":false},{"name":"Hannah Jauncey","is_ca":false},{"name":"Samaneh Kouchaki","is_ca":false},{"name":"Farhad Nooralahzadeh","is_ca":false},{"name":"Lei Clifton","is_ca":false},{"name":"Laura Merson","is_ca":false},{"name":"David A. Clifton","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01169029268271533,"gpt":0.3042427404396033,"spread":0.2925524477568879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002547574,0.001314109,0.000578846,0.001684292,0.0003493985,0.00183358,0.002084572,0.0009072938,0.01351506],"category_scores_gemma":[0.01545823,0.0007173746,0.001319676,0.001254858,0.00108187,0.006130395,0.003767738,0.00317759,0.008818846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0015542,"about_ca_system_score_gemma":0.002915381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003133788,"about_ca_topic_score_gemma":0.00571743,"domain_scores_codex":[0.9976996,0.0007538392,0.0002667524,0.0005486269,0.0006125403,0.000118685],"domain_scores_gemma":[0.9932497,0.003799125,0.000349893,0.001610354,0.0007749989,0.0002160207],"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":[0.001062609,0.0004112517,0.004386563,0.00102061,0.0001779017,0.0005135506,0.0004802328,0.1242555,0.01213633,0.05540857,0.06832554,0.7318212],"study_design_scores_gemma":[0.0001211837,0.0002119466,0.0004786034,0.0001226599,0.00006660144,0.0003604522,0.0001489833,0.8164868,0.01593537,0.1236837,0.04232388,0.00005985633],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01791121,0.001352246,0.8986432,0.002445353,0.00032328,0.0005248201,0.005984173,0.06904554,0.003770186],"genre_scores_gemma":[0.3717313,0.001273559,0.5995435,0.00144167,0.0002141247,0.0006950929,0.01659666,0.002284962,0.006219259],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01351506,"threshold_uncertainty_score":0.04521239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167742478","doi":"10.1017/s1351324911000210","title":"Exploring patterns in dictionary definitions for synonym extraction","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Synonym (taxonomy); Natural language processing; Artificial intelligence; Lexicon; Quality (philosophy)","authors":[{"name":"Tong Wang","is_ca":true},{"name":"Graeme Hirst","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07898671688241453,"gpt":0.262412322812195,"spread":0.1834256059297805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001432529,0.0007350294,0.0008512812,0.006610184,0.0006504231,0.001961044,0.001229422,0.0007510275,0.003704714],"category_scores_gemma":[0.01259195,0.0003608092,0.0006039606,0.006033116,0.0006208949,0.003780595,0.001538513,0.0008603398,0.00202924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003771082,"about_ca_system_score_gemma":0.001045231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006590036,"about_ca_topic_score_gemma":0.001590148,"domain_scores_codex":[0.9965746,0.001265796,0.0006540861,0.0007691701,0.0006452357,0.00009114416],"domain_scores_gemma":[0.991148,0.005068125,0.001169496,0.001052829,0.00135505,0.0002064839],"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":[0.0003552286,0.0003850016,0.02054571,0.002177106,0.0002336072,0.0009618346,0.001302061,0.003692244,0.05378551,0.01154123,0.01035438,0.8946661],"study_design_scores_gemma":[0.0004227407,0.001115722,0.05425603,0.001331186,0.0006685416,0.01048364,0.007544276,0.4933141,0.1867034,0.08120048,0.162617,0.0003428108],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1714958,0.002264994,0.8057359,0.000957816,0.0002046421,0.000964707,0.00617021,0.004711158,0.007494718],"genre_scores_gemma":[0.3398907,0.0007448734,0.651971,0.0001106264,0.00005296311,0.0002647203,0.005856051,0.0002179523,0.0008910684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006610184,"threshold_uncertainty_score":0.01239353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4384694635","doi":"10.1017/s1351324923000360","title":"Describe the house and I will tell you the price: House price prediction with textual description data","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Housing Market and Economics","field":"Economics, Econometrics and Finance","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 Ottawa","funders":"","keywords":"Word2vec; Computer science; House price; Boosting (machine learning); Word embedding; Artificial intelligence; Word (group theory); Machine learning; Information retrieval; Data mining; Natural language processing; Embedding; Econometrics; Linguistics; Mathematics","authors":[{"name":"Hanxiang Zhang","is_ca":true},{"name":"Yansong Li","is_ca":true},{"name":"Paula Branco","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.019698140741209,"gpt":0.1919614610952497,"spread":0.1722633203540407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004802009,0.0005596789,0.0002248047,0.0008193167,0.0001248023,0.0004210373,0.0003831632,0.0005691121,0.002966457],"category_scores_gemma":[0.003120416,0.0001449446,0.0003453452,0.001045962,0.0001413601,0.0009412819,0.0002443257,0.0007261248,0.001434272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004103937,"about_ca_system_score_gemma":0.0001741055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01126127,"about_ca_topic_score_gemma":0.01441333,"domain_scores_codex":[0.9997572,0.00008138671,0.00001912245,0.00005432848,0.00006127195,0.00002676059],"domain_scores_gemma":[0.9984233,0.0009687687,0.0001884503,0.0001122131,0.0002426933,0.0000645632],"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":[0.002523609,0.002144874,0.2926515,0.0006068831,0.0003364012,0.001450582,0.0002970294,0.1994756,0.01332016,0.002329704,0.0563114,0.4285522],"study_design_scores_gemma":[0.00002376966,0.00009937906,0.04078977,0.00002168078,0.00003105765,0.0001031827,0.0001104604,0.9517146,0.00391574,0.0009251154,0.002246186,0.00001888222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9694806,0.0004131843,0.01739867,0.0006975008,0.0001302405,0.00004331527,0.008567474,0.0008983325,0.002370748],"genre_scores_gemma":[0.9665816,0.0001642593,0.01680885,0.00009461131,0.00007013551,0.00003153685,0.01363163,0.00002960698,0.002587766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01126127,"threshold_uncertainty_score":0.0223915,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159087629","doi":"10.1017/s1351324911000118","title":"A hierarchical approach to mood classification in blogs","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","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 Ottawa","funders":"","keywords":"Computer science; Task (project management); Mood; Hierarchy; Set (abstract data type); Artificial intelligence; Machine learning; Sentiment analysis; Training set; Orientation (vector space); Natural language processing; Data set; Psychology","authors":[{"name":"Fazel Keshtkar","is_ca":true},{"name":"Diana Inkpen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01986886967877055,"gpt":0.2344160687173866,"spread":0.214547199038616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001803344,0.0006212797,0.0007031769,0.004992743,0.001304699,0.00146588,0.0009722869,0.0006596461,0.00336616],"category_scores_gemma":[0.005758482,0.0003640403,0.000856318,0.002895956,0.0004723055,0.00140086,0.001161119,0.001118101,0.001642082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008648356,"about_ca_system_score_gemma":0.0008609396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007534523,"about_ca_topic_score_gemma":0.01445476,"domain_scores_codex":[0.9985702,0.0005194987,0.0001259677,0.0003350371,0.0002834774,0.0001658776],"domain_scores_gemma":[0.9969832,0.001268452,0.0002910272,0.0003495168,0.0009519132,0.0001558324],"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":[0.0005427099,0.0007141877,0.02854161,0.0003931781,0.0001839021,0.0002282699,0.0007308711,0.0218008,0.02618913,0.007007012,0.02474129,0.8889271],"study_design_scores_gemma":[0.00007053383,0.000153153,0.02397913,0.00007315566,0.00009569492,0.0001214147,0.0003889947,0.9333439,0.007116538,0.02814004,0.006457412,0.00005996676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1727786,0.001660894,0.8058171,0.001035917,0.0003098799,0.0006369724,0.003244776,0.004589925,0.009926039],"genre_scores_gemma":[0.6503054,0.0003288226,0.3410214,0.0001837088,0.0002999123,0.0003539719,0.003522174,0.0001899118,0.003794614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007534523,"threshold_uncertainty_score":0.01498133,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971541835","doi":"10.1017/s1351324901002650","title":"Real-time automatic insertion of accents in French text","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Stress (linguistics); Character (mathematics); Word (group theory); Natural language processing; Speech recognition; Artificial intelligence; Linguistics","authors":[{"name":"Michel Simard","is_ca":true},{"name":"Alexandre Deslauriers","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004005314190147125,"gpt":0.2351412818868485,"spread":0.2311359676967014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001401203,0.001154992,0.0009666161,0.001174049,0.0006261873,0.00142682,0.00119014,0.001031193,0.003024106],"category_scores_gemma":[0.006837665,0.000530306,0.0004558305,0.0007558131,0.0004971249,0.001312222,0.0007186154,0.000709944,0.003942902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004122255,"about_ca_system_score_gemma":0.0003945769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00334785,"about_ca_topic_score_gemma":0.003129347,"domain_scores_codex":[0.9982893,0.0003873527,0.0001304231,0.0006274214,0.0004265576,0.0001389904],"domain_scores_gemma":[0.9937927,0.003062489,0.0007950116,0.0008634774,0.001270731,0.0002156601],"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":[0.001418172,0.0001691255,0.004771527,0.0003489088,0.00005188015,0.0006757259,0.001233807,0.004842542,0.2464894,0.0006641109,0.007666714,0.7316681],"study_design_scores_gemma":[0.0001390378,0.001122485,0.01732076,0.00005542443,0.0001541986,0.002935682,0.0007104808,0.4064515,0.5390128,0.001573505,0.03024299,0.0002810932],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3740987,0.0009015515,0.5044219,0.000400426,0.0003857067,0.0002384086,0.0009805821,0.1153299,0.003242901],"genre_scores_gemma":[0.6085649,0.0003013437,0.3812218,0.0001651093,0.0001537071,0.0000858154,0.001466943,0.001607906,0.006432465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00334785,"threshold_uncertainty_score":0.01011664,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3042081424","doi":"10.1017/s1351324920000376","title":"Negation detection for sentiment analysis: A case study in Spanish","year":2020,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":20,"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":"Negation; Computer science; Natural language processing; Sentiment analysis; Scope (computer science); Artificial intelligence; Identification (biology); Task (project management); Context (archaeology); Programming language","authors":[{"name":"Salud María Jiménez-Zafra","is_ca":false},{"name":"Noa P. Cruz-Díaz","is_ca":false},{"name":"Maite Taboada","is_ca":true},{"name":"María Teresa Martín Valdivia","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01139807628053087,"gpt":0.2587706953524957,"spread":0.2473726190719649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00331386,0.0005136232,0.0003455384,0.001134208,0.001231208,0.001371959,0.0006932235,0.001134985,0.001696068],"category_scores_gemma":[0.01494695,0.0001331724,0.0003641557,0.001326914,0.0008062138,0.0007626982,0.0008675499,0.0007104811,0.0006390769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001786438,"about_ca_system_score_gemma":0.001302067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02677096,"about_ca_topic_score_gemma":0.02742238,"domain_scores_codex":[0.9981489,0.000820623,0.0001319818,0.0001912129,0.0005768647,0.0001304187],"domain_scores_gemma":[0.9907273,0.004992947,0.0004519163,0.0004346128,0.003109148,0.0002840405],"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":[0.001373309,0.001772458,0.2292416,0.002149657,0.0001931768,0.0669272,0.05179111,0.01317972,0.04778922,0.01101592,0.06201313,0.5125535],"study_design_scores_gemma":[0.0004788444,0.0009117337,0.2258507,0.001156321,0.0003529171,0.02773874,0.08349016,0.1435168,0.07639556,0.01781275,0.4220212,0.0002743996],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9430915,0.001052574,0.02773303,0.004267292,0.0002074285,0.0003392085,0.001200514,0.0006649056,0.0214435],"genre_scores_gemma":[0.9635313,0.0007975101,0.02725538,0.0007197736,0.00008423092,0.0001044484,0.001089483,0.0003364096,0.006081631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02677096,"threshold_uncertainty_score":0.05323023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089752704","doi":"10.1017/s1351324910000264","title":"Subjectivity detection in spoken and written conversations","year":2010,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","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 British Columbia","funders":"","keywords":"Computer science; Conversation; Set (abstract data type); Subjectivity; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Speech recognition; Linguistics","authors":[{"name":"Gabriel Murray","is_ca":true},{"name":"Giuseppe Carenini","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.002443327476115435,"gpt":0.2036302636457611,"spread":0.2011869361696457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001883076,0.0005442384,0.0006124842,0.001963086,0.0004800537,0.001674619,0.0004079836,0.0006262721,0.001752344],"category_scores_gemma":[0.01224261,0.0002386077,0.0004285594,0.0006342608,0.0003836787,0.001720808,0.001360228,0.000666285,0.001035817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003176414,"about_ca_system_score_gemma":0.0003263499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001030067,"about_ca_topic_score_gemma":0.001260056,"domain_scores_codex":[0.9977198,0.001128231,0.000144474,0.0004146763,0.0004015302,0.0001911779],"domain_scores_gemma":[0.9871702,0.008338367,0.00150946,0.0006451843,0.001837917,0.0004989072],"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":[0.003731202,0.0004673279,0.1683859,0.001006795,0.0003521089,0.0009166583,0.006668733,0.006883617,0.2173937,0.001581354,0.004389219,0.5882233],"study_design_scores_gemma":[0.0001339431,0.001170542,0.4290987,0.000268639,0.0003015332,0.001640819,0.008980107,0.370879,0.1655548,0.00974896,0.01192694,0.0002960385],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9308406,0.0004555659,0.0595058,0.0002215166,0.0001106153,0.0001872997,0.000850048,0.0009259195,0.006902582],"genre_scores_gemma":[0.979815,0.0001404217,0.01758084,0.00005431483,0.00008910652,0.00007944891,0.0007097833,0.00006454933,0.001466422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001963086,"threshold_uncertainty_score":0.009958744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385552004","doi":"10.1017/s1351324923000396","title":"SSL-GAN-RoBERTa: A robust semi-supervised model for detecting Anti-Asian COVID-19 hate speech on social media","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Hate Speech and Cyberbullying Detection","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 Ottawa","funders":"","keywords":"Computer science; Social media; Transformer; Artificial intelligence; Task (project management); Coronavirus disease 2019 (COVID-19); Machine learning; Speech recognition; Data mining; Voltage","authors":[{"name":"Xuanyu Su","is_ca":true},{"name":"Yansong Li","is_ca":true},{"name":"Paula Branco","is_ca":true},{"name":"Diana Inkpen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0259402050914098,"gpt":0.260374998053483,"spread":0.2344347929620732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002311956,0.001719448,0.001717782,0.0008338332,0.000455607,0.0008462311,0.00315919,0.001744741,0.001455613],"category_scores_gemma":[0.00418978,0.0006216286,0.001387635,0.000531763,0.001029097,0.001371356,0.001085288,0.002725637,0.001308821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041063,"about_ca_system_score_gemma":0.001264279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008012514,"about_ca_topic_score_gemma":0.01167347,"domain_scores_codex":[0.9987592,0.0005046765,0.00004899474,0.0004282052,0.0001427317,0.0001161229],"domain_scores_gemma":[0.9975339,0.001413571,0.0002039173,0.0002463929,0.0004856906,0.0001164806],"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":[0.0006537822,0.0006043523,0.005909202,0.0002950033,0.000256897,0.0002801048,0.000222048,0.7308505,0.007111074,0.003889795,0.01958827,0.230339],"study_design_scores_gemma":[0.000007908388,0.00002769502,0.0001835398,0.000006154762,0.000007848043,0.0000156707,0.000007023236,0.9980325,0.0005112425,0.0009153783,0.0002783062,0.000006784386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1216641,0.002792612,0.8560622,0.001752146,0.0004022237,0.0004246563,0.002026937,0.009575964,0.005299156],"genre_scores_gemma":[0.8490756,0.0005371608,0.1323422,0.001404941,0.0003266677,0.0005622672,0.005449168,0.0003768436,0.009925169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008012514,"threshold_uncertainty_score":0.01593173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4284891255","doi":"10.1017/s1351324922000298","title":"Neural automated writing evaluation for Korean L2 writing","year":2022,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Fluency; Parsing; Artificial intelligence; Natural language processing; Complement (music); Artificial neural network; Reliability (semiconductor); Linguistics","authors":[{"name":"KyungTae Lim","is_ca":false},{"name":"Jayoung Song","is_ca":false},{"name":"Jungyeul Park","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009429505732520903,"gpt":0.2826202360865886,"spread":0.2731907303540677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001727313,0.0005999577,0.0004757668,0.0007560675,0.0002955302,0.0008095186,0.0005996384,0.0005294825,0.00307666],"category_scores_gemma":[0.006318429,0.0001678512,0.0002603517,0.0004179789,0.0002149736,0.001215962,0.0008776243,0.0006184797,0.0009598836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005204431,"about_ca_system_score_gemma":0.0004248036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003281021,"about_ca_topic_score_gemma":0.004698254,"domain_scores_codex":[0.9989942,0.0003936054,0.00008677573,0.0002416278,0.0002196549,0.00006418909],"domain_scores_gemma":[0.9969832,0.001290392,0.0001992461,0.0003534463,0.00106239,0.0001113694],"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":[0.000856516,0.0007615199,0.01497685,0.0002829027,0.0001365356,0.0003618718,0.0003668208,0.03957462,0.05595846,0.0008169355,0.005015559,0.8808915],"study_design_scores_gemma":[0.0000468855,0.0003766963,0.01378827,0.00002541867,0.00003811423,0.0001306478,0.0002227992,0.936131,0.04696518,0.0005771233,0.001661824,0.00003604909],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.85569,0.0004251754,0.1313166,0.0002155936,0.000126466,0.0002188127,0.0007683676,0.006594815,0.004644107],"genre_scores_gemma":[0.9523484,0.00008083415,0.04262829,0.00006455019,0.00001385547,0.00009429042,0.001001994,0.00007833339,0.003689525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003281021,"threshold_uncertainty_score":0.01029247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2763406350","doi":"10.1017/s1351324917000389","title":"Emerging trends: A tribute to Charles Wayne","year":2017,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Alberta-Pacific Forest Industries","keywords":"Tribute; Order (exchange); Government (linguistics); Computer science; sort; Management; Law; Political science; Economics; Finance; Philosophy; Linguistics","authors":[{"name":"Kenneth Church","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007743718129550689,"gpt":0.2627037147876462,"spread":0.2549599966580955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01575915,0.0008568791,0.001296116,0.002975717,0.00730182,0.01879287,0.002249162,0.01369907,0.01305297],"category_scores_gemma":[0.06165123,0.0005650222,0.0006774482,0.002038947,0.01590315,0.0209041,0.005554382,0.03634271,0.007030458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007031415,"about_ca_system_score_gemma":0.01007814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01167378,"about_ca_topic_score_gemma":0.01560226,"domain_scores_codex":[0.9876981,0.00301545,0.00075471,0.002505049,0.004855263,0.001171379],"domain_scores_gemma":[0.9398977,0.02688215,0.001646178,0.002938163,0.01664133,0.01199459],"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":[0.00000753417,0.00001268468,0.0001305125,0.00002532079,0.000007557543,0.00008738761,0.0005173594,0.00003871291,0.00004627972,0.0289161,0.9585378,0.01167274],"study_design_scores_gemma":[0.000005302369,0.000006687856,0.0001061897,0.0002026514,0.000002902199,0.00008466801,0.0006347001,0.00005775668,0.00006543404,0.01618713,0.9826272,0.00001930467],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0001949029,0.006781965,0.0003568605,0.9697303,0.01812965,0.000003617344,0.00002496879,0.00003502002,0.004742795],"genre_scores_gemma":[0.02019995,0.02047021,0.00173568,0.8359513,0.04726695,0.00006192995,0.0001002436,0.0004720258,0.07374173],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.01879287,"threshold_uncertainty_score":0.08334339,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2946534924","doi":"10.1017/s1351324919000135","title":"NLP commercialisation in the last 25 years","year":2019,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Focus (optics); Quarter (Canadian coin); Point (geometry); Artificial intelligence; Natural (archaeology); Natural language processing; History","authors":[{"name":"Robert Dale","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004465130453185606,"gpt":0.2309133449031753,"spread":0.2264482144499897,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01761813,0.0005368338,0.0005158945,0.004283735,0.001805093,0.01221795,0.001675269,0.003228772,0.01764651],"category_scores_gemma":[0.04183691,0.0004041718,0.0006015472,0.005201023,0.003560209,0.01160289,0.004659221,0.003371062,0.005631595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005496271,"about_ca_system_score_gemma":0.004207455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002581159,"about_ca_topic_score_gemma":0.002225254,"domain_scores_codex":[0.9913591,0.001415462,0.0006569955,0.001473954,0.004499013,0.0005955768],"domain_scores_gemma":[0.9472823,0.01798301,0.00483877,0.003242474,0.02193808,0.004715478],"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":[0.0003432107,0.0001881833,0.003363188,0.001899294,0.00006387653,0.001178053,0.001870006,0.0007152286,0.005005743,0.1302418,0.2953866,0.5597448],"study_design_scores_gemma":[0.00001234714,0.00004129281,0.003075311,0.0005107394,0.00001249894,0.0004304209,0.0006200393,0.0006243361,0.001514131,0.006982847,0.9861501,0.00002591763],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"review","genre_scores_codex":[0.09056501,0.2812316,0.01973002,0.2448117,0.03075584,0.0002643687,0.004360357,0.003947172,0.324334],"genre_scores_gemma":[0.5040691,0.1710141,0.0435793,0.0524586,0.01940721,0.0004045461,0.01350756,0.004485907,0.1910737],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01764651,"threshold_uncertainty_score":0.09317464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157616430","doi":"10.1017/s1351324908004737","title":"Multilingual pronunciation by analogy","year":2008,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","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":"National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Pronunciation; Transcription (linguistics); Natural language processing; Orthography; Spelling; Analogy; Artificial intelligence; Variation (astronomy); Phonetic transcription; Linguistics; Speech recognition","authors":[{"name":"Tasanawan Soonklang","is_ca":false},{"name":"R.I. Damper","is_ca":false},{"name":"Yannick Marchand","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004698680563171272,"gpt":0.2267604826131823,"spread":0.222061802050011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001199816,0.0006079079,0.0006839917,0.001232567,0.0004237048,0.001053403,0.0005085975,0.0002958945,0.006994685],"category_scores_gemma":[0.0062983,0.0001882266,0.0003667937,0.001202989,0.0003700492,0.001019016,0.001790664,0.0005154685,0.00312415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003426942,"about_ca_system_score_gemma":0.0004347434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002463143,"about_ca_topic_score_gemma":0.002777558,"domain_scores_codex":[0.9972864,0.001152071,0.0002242442,0.0007270664,0.0004674042,0.0001427245],"domain_scores_gemma":[0.9961959,0.001905998,0.0001953385,0.0007666585,0.0008723659,0.00006371822],"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":[0.0009046461,0.0001609845,0.02427738,0.0006529787,0.0001559904,0.0008648525,0.001665835,0.03083773,0.1065263,0.003973408,0.003456933,0.8265229],"study_design_scores_gemma":[0.000340774,0.00244945,0.1138966,0.0002789791,0.0003339614,0.007825371,0.004455219,0.4234966,0.3134658,0.02434671,0.1088122,0.0002984475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6555782,0.001410685,0.3097917,0.0002586707,0.0002213025,0.0001982743,0.001941403,0.005632005,0.02496775],"genre_scores_gemma":[0.9396645,0.0001641319,0.05512645,0.00004866818,0.00002992455,0.00005087968,0.001823041,0.0002470964,0.00284518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006994685,"threshold_uncertainty_score":0.02339959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382542296","doi":"10.1017/s1351324923000311","title":"Korean named entity recognition based on language-specific features","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Morpheme; Natural language processing; Artificial intelligence; Annotation; Named-entity recognition; Scheme (mathematics); Ambiguity; Segmentation; Syllable; Word (group theory); Speech recognition; Task (project management); Linguistics","authors":[{"name":"Yige Chen","is_ca":false},{"name":"KyungTae Lim","is_ca":false},{"name":"Jungyeul Park","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01003904351749246,"gpt":0.2231050327943933,"spread":0.2130659892769008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001061351,0.0006478449,0.0006658632,0.001207068,0.0002925924,0.001009352,0.0009313821,0.0005183435,0.001617413],"category_scores_gemma":[0.002474282,0.0001883506,0.0008842655,0.001480123,0.000253569,0.003891006,0.0006673241,0.0006798471,0.001289908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003224537,"about_ca_system_score_gemma":0.000385711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003517365,"about_ca_topic_score_gemma":0.0050681,"domain_scores_codex":[0.9993898,0.0001613372,0.00005693959,0.0002323803,0.0001051049,0.0000544218],"domain_scores_gemma":[0.998647,0.0004862421,0.0001237759,0.0003296444,0.0003699043,0.00004335548],"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":[0.0005904056,0.0002498176,0.01550482,0.0003344833,0.0003655965,0.0004507175,0.0002859675,0.1545227,0.06398987,0.008916793,0.006826218,0.7479627],"study_design_scores_gemma":[0.000007149756,0.00005276056,0.004027413,0.00001622231,0.00009007432,0.0001378311,0.00007113719,0.964128,0.02601821,0.001780527,0.003634497,0.00003616003],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1557474,0.0008731891,0.8316519,0.0002788003,0.0001731523,0.0001065028,0.001078384,0.005788933,0.004301824],"genre_scores_gemma":[0.7500292,0.0005328913,0.2423421,0.00008902161,0.00004631277,0.00006321108,0.003723466,0.0001840015,0.0029897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003517365,"threshold_uncertainty_score":0.006993771,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121929533","doi":"10.1017/s135132491300003x","title":"Designing a machine translation system for Canadian weather warnings: A case study","year":2013,"lang":"en","type":"article","venue":"Natural Language Engineering","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":true},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Metric (unit); Task (project management); Quality (philosophy); Domain (mathematical analysis); Evaluation of machine translation; Translation (biology); Artificial intelligence; Machine translation software usability; Presentation (obstetrics); Example-based machine translation; Machine learning; Information retrieval; Systems engineering","authors":[{"name":"Fabrizio Gotti","is_ca":true},{"name":"Philippe Langlais","is_ca":true},{"name":"Guy Lapalme","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007204560510228801,"gpt":0.2309438070816249,"spread":0.2237392465713961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002710951,0.0009796236,0.0005564202,0.001139473,0.004927296,0.001920437,0.001129827,0.001587223,0.005915688],"category_scores_gemma":[0.007593164,0.0003482535,0.000538849,0.002144947,0.001242524,0.001367709,0.0008197958,0.001351616,0.002190729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008337611,"about_ca_system_score_gemma":0.0147688,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.521345,"about_ca_topic_score_gemma":0.5472217,"domain_scores_codex":[0.9975339,0.0008231773,0.0001674146,0.0003248387,0.000886985,0.000263678],"domain_scores_gemma":[0.9959973,0.001338392,0.0001337028,0.0002910118,0.00196921,0.0002703783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001258779,0.001557392,0.01869067,0.003564319,0.0001640063,0.01706613,0.03291257,0.06469399,0.1513133,0.01636749,0.0978449,0.5945664],"study_design_scores_gemma":[0.0009629357,0.001280639,0.04283557,0.0003545198,0.0003659773,0.00567271,0.02468216,0.1524724,0.230423,0.003487006,0.536755,0.0007080379],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7345998,0.001326954,0.1734568,0.006377378,0.0007575516,0.003353867,0.006681444,0.01415146,0.05929474],"genre_scores_gemma":[0.7016811,0.0008062366,0.2492581,0.0006128695,0.00009801871,0.0004151243,0.00822524,0.001440102,0.03746321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.478655,"threshold_uncertainty_score":0.9629477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226024751","doi":"10.1017/s1351324922000134","title":"Real-world sentence boundary detection using multitask learning: A case study on French","year":2022,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Hanbat National University","keywords":"Computer science; Sentence; Punctuation; Natural language processing; Task (project management); Artificial intelligence; Boundary (topology); Multi-task learning; Speech recognition","authors":[{"name":"KyungTae Lim","is_ca":false},{"name":"Jungyeul Park","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01083990589589887,"gpt":0.2761478394611767,"spread":0.2653079335652778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002485326,0.0008659191,0.0005160004,0.001920444,0.001549806,0.001315851,0.001101493,0.001910853,0.001264634],"category_scores_gemma":[0.01215881,0.0001517594,0.0005616944,0.001707702,0.00075051,0.001325161,0.0007214783,0.0007789317,0.0007463995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269524,"about_ca_system_score_gemma":0.0007627204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03128308,"about_ca_topic_score_gemma":0.04338316,"domain_scores_codex":[0.9972603,0.001534842,0.0001538556,0.0004492524,0.0004378481,0.0001638569],"domain_scores_gemma":[0.9872562,0.008560916,0.0006162623,0.0009797586,0.002082011,0.000504921],"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":[0.003340783,0.003347955,0.1141322,0.003781487,0.0007039466,0.03303708,0.01725966,0.06382222,0.08793525,0.006566803,0.09650704,0.5695656],"study_design_scores_gemma":[0.0006159162,0.002433633,0.2399611,0.0004910034,0.0004445428,0.01229638,0.01976743,0.4120922,0.1236983,0.01337952,0.1742778,0.0005421676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9574623,0.001284699,0.02884295,0.001378357,0.0001512362,0.0002353815,0.003811116,0.002708739,0.004125145],"genre_scores_gemma":[0.9515767,0.0002393936,0.03930082,0.000377801,0.000102889,0.0001506852,0.005928485,0.0001912287,0.002132082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03128308,"threshold_uncertainty_score":0.06220198,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058214962","doi":"10.1017/s1351324913000090","title":"On the semantics of noun compounds","year":2013,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Automatic summarization; Computer science; Noun; Natural language processing; Cover (algebra); Artificial intelligence; Proper noun; Semantics (computer science); Subject (documents); Machine translation; Linguistics; Noun phrase; Question answering; Sequence (biology); World Wide Web; Programming language; Philosophy; Chemistry","authors":[{"name":"Stan Śzpakowicz","is_ca":true},{"name":"Francis Bond","is_ca":false},{"name":"Preslav Nakov","is_ca":false},{"name":"Su Nam Kim","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.003863718336442225,"gpt":0.2078067341440626,"spread":0.2039430158076204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00318155,0.001064407,0.00106129,0.004041028,0.004044357,0.007120886,0.001864051,0.002482488,0.007287153],"category_scores_gemma":[0.008473878,0.001052969,0.001464369,0.004216988,0.01209594,0.02882442,0.004231349,0.004341386,0.002243806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00262255,"about_ca_system_score_gemma":0.00156447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004520501,"about_ca_topic_score_gemma":0.003227541,"domain_scores_codex":[0.9972754,0.001136836,0.000332074,0.0005471251,0.0005376029,0.0001710334],"domain_scores_gemma":[0.9946545,0.003259754,0.0003178092,0.0006482168,0.0009365739,0.0001830891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002055672,0.000009426374,0.0001072172,0.00006747326,0.000008885433,0.000112901,0.000912689,0.0005753877,0.0004052586,0.986385,0.002691369,0.008703816],"study_design_scores_gemma":[0.000007405916,0.000008140606,0.00009701839,0.00006213915,0.000008317053,0.000111003,0.0002735755,0.001908651,0.0002905811,0.9665482,0.03067159,0.00001344465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03598279,0.03237357,0.7207747,0.02252554,0.002481143,0.0001801301,0.001352517,0.001038715,0.1832909],"genre_scores_gemma":[0.6532979,0.02324862,0.2758824,0.006891634,0.004221934,0.0005023979,0.002474962,0.001529569,0.03195057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007287153,"threshold_uncertainty_score":0.02437794,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129913068","doi":"10.1017/s135132491100012x","title":"Learning opinions in user-generated web content","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","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":"Université de Montréal; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Computer science; Construct (python library); Information retrieval; Product (mathematics); Hierarchy; User-generated content; Natural language processing; Sentiment analysis; World Wide Web; Artificial intelligence; Web content; Web page; Social media","authors":[{"name":"Marina Sokolova","is_ca":true},{"name":"Guy Lapalme","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02241642151835773,"gpt":0.2265547629684585,"spread":0.2041383414501008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001849696,0.0004310928,0.0003565447,0.001793233,0.0001875816,0.001105185,0.0003854392,0.0006021297,0.0007709409],"category_scores_gemma":[0.01515825,0.0001573468,0.0003599691,0.0008029094,0.0002418604,0.001270212,0.0003113977,0.0005389194,0.0004730568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006769084,"about_ca_system_score_gemma":0.0001890289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001689194,"about_ca_topic_score_gemma":0.001800506,"domain_scores_codex":[0.9985373,0.0007574063,0.00008613331,0.0002296275,0.0002972153,0.00009230019],"domain_scores_gemma":[0.9877766,0.00842526,0.001126008,0.0003295978,0.002115442,0.0002270176],"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":[0.002365107,0.001708509,0.3310988,0.0004893154,0.0006008016,0.0009332584,0.002012473,0.0947165,0.03498821,0.002436769,0.007866274,0.520784],"study_design_scores_gemma":[0.0000208124,0.000237782,0.04784221,0.00001882984,0.00004829909,0.00007225502,0.0003004059,0.9432367,0.005962669,0.001559007,0.0006785405,0.00002242273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655349,0.0001448245,0.0319426,0.0001892419,0.00003474536,0.00008669934,0.0004731928,0.0002430043,0.001350728],"genre_scores_gemma":[0.990086,0.00003981028,0.00870347,0.00002652989,0.00003648583,0.00002639427,0.0007265876,0.0000123561,0.0003424608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001849696,"threshold_uncertainty_score":0.009782255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052696540","doi":"10.1017/s1351324908005044","title":"A corpus-based analysis of argument realization by preposition structures","year":2009,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"FrameNet; Computer science; Realization (probability); Argument (complex analysis); Natural language processing; Artificial intelligence; Semantics (computer science); Semantic role labeling; Linguistics; Frame (networking); Parsing; Programming language; Sentence; Mathematics; Philosophy","authors":[{"name":"Qibo Zhu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00247665107588323,"gpt":0.231932056132034,"spread":0.2294554050561508,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002092654,0.0002466572,0.0003711035,0.005341295,0.001462542,0.001467859,0.0004965686,0.0005144405,0.004040629],"category_scores_gemma":[0.01261777,0.0003625049,0.0003103323,0.007999713,0.001166901,0.001897865,0.00112625,0.0009275149,0.0007643197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008323531,"about_ca_system_score_gemma":0.0007376922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003706906,"about_ca_topic_score_gemma":0.00682637,"domain_scores_codex":[0.9984251,0.000729441,0.0001376307,0.0002866706,0.0003763405,0.00004481828],"domain_scores_gemma":[0.9830623,0.01269167,0.0007958252,0.001841793,0.001497097,0.0001113601],"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":[0.002974237,0.001045894,0.08902512,0.00493756,0.0005355668,0.004548921,0.03727122,0.01724724,0.1139607,0.1561602,0.04581229,0.526481],"study_design_scores_gemma":[0.0003167903,0.0005579501,0.3761575,0.001003218,0.0005212199,0.005092378,0.02247181,0.09639845,0.09831809,0.04614159,0.3526553,0.0003658215],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8877897,0.001713226,0.0697191,0.000503052,0.0001970294,0.0002706545,0.0175173,0.0006122798,0.02167762],"genre_scores_gemma":[0.9089435,0.0008246829,0.06358326,0.00005518123,0.0000522552,0.0003608384,0.0236302,0.0002401198,0.002309964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005341295,"threshold_uncertainty_score":0.01351726,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136433925","doi":"10.1017/s1351324903003231","title":"Surface-marker-based dialog modelling: A progress report on the MAREDI project","year":2003,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","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":"University of Ottawa; Université Laval; Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Dialog box; Natural language processing; Connectionism; Semantics (computer science); Conversation; Spoken language; Artificial intelligence; Natural language; Natural language understanding; Natural language generation; Programming language; Linguistics; Artificial neural network; World Wide Web","authors":[{"name":"Sylvain Delisle","is_ca":true},{"name":"Bernard Moulin","is_ca":true},{"name":"Terry Copeck","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01414064130185601,"gpt":0.2556672043902133,"spread":0.2415265630883573,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00520351,0.001566546,0.001476278,0.001712064,0.0006050625,0.003695744,0.003917031,0.001760912,0.006767148],"category_scores_gemma":[0.009961942,0.001177774,0.001317509,0.0008961253,0.001237336,0.006930334,0.002082811,0.002287299,0.003020507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001487556,"about_ca_system_score_gemma":0.002075558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008152458,"about_ca_topic_score_gemma":0.003254762,"domain_scores_codex":[0.9970733,0.001169612,0.000153832,0.0007974995,0.0006886908,0.0001171541],"domain_scores_gemma":[0.9958973,0.001665477,0.0001941526,0.001286248,0.0007296593,0.0002272975],"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":[0.0009064373,0.0009860353,0.003115988,0.001627226,0.0002261355,0.0003854085,0.002563362,0.1083626,0.05537347,0.08220652,0.01730042,0.7269464],"study_design_scores_gemma":[0.0001438929,0.0003798252,0.002320602,0.0002152151,0.0001401563,0.0004373496,0.0003914485,0.8023509,0.04921948,0.01892229,0.1252776,0.0002013519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03500116,0.003510033,0.9349026,0.001009603,0.0001794839,0.0006575201,0.001243248,0.01404126,0.009455197],"genre_scores_gemma":[0.130238,0.002664106,0.8516697,0.0001895908,0.0001872902,0.0004309211,0.003429024,0.001429537,0.009761753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008152458,"threshold_uncertainty_score":0.02751917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3009120927","doi":"10.1017/s1351324920000133","title":"Nonuniform language in technical writing: Detection and correction","year":2020,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Text Readability and Simplification","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":"Dalhousie University","funders":"","keywords":"Computer science; Natural language processing; Readability; Paraphrase; Artificial intelligence; Task (project management); Sentence; Context (archaeology); Synonym (taxonomy); Similarity (geometry); Programming language","authors":[{"name":"Weibo Wang","is_ca":true},{"name":"Aminul Islam","is_ca":false},{"name":"Abidalrahman Moh’d","is_ca":false},{"name":"Axel J. Soto","is_ca":false},{"name":"Evangelos Milios","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004691055894078967,"gpt":0.2111093347640541,"spread":0.2064182788699751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002517057,0.0007549339,0.0007767307,0.003692467,0.0005696944,0.001443587,0.001358109,0.0009198388,0.001872491],"category_scores_gemma":[0.02126579,0.0002754679,0.0004257892,0.001871773,0.0007842088,0.001401531,0.001260595,0.0007797249,0.001368931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004416045,"about_ca_system_score_gemma":0.0007622358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001494144,"about_ca_topic_score_gemma":0.002392773,"domain_scores_codex":[0.994359,0.001703235,0.0006724451,0.001367154,0.001706475,0.000191709],"domain_scores_gemma":[0.9651965,0.01417776,0.006305132,0.004721452,0.00898364,0.0006154729],"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":[0.0005393249,0.0002372673,0.03639319,0.0008363486,0.0001126843,0.001083014,0.001238386,0.00717105,0.1343645,0.00142319,0.005936398,0.8106646],"study_design_scores_gemma":[0.00008156999,0.0004277505,0.06568927,0.0001494466,0.0001564265,0.003954249,0.001395993,0.5438369,0.3640112,0.003659832,0.01646955,0.000167804],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.439561,0.00117953,0.5450733,0.0005878599,0.0002421043,0.000353356,0.0007644815,0.008713036,0.003525352],"genre_scores_gemma":[0.7216517,0.0002507121,0.2740336,0.0001132615,0.00008261161,0.00009201342,0.0008960045,0.0003815953,0.002498537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003692467,"threshold_uncertainty_score":0.01331162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160938081","doi":"10.1017/s1351324912000289","title":"Modeling human newspaper readers: The Fuzzy Believer approach","year":2012,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Newspaper; Computer science; Fuzzy logic; Set (abstract data type); Artificial intelligence; Range (aeronautics); Natural (archaeology); Fuzzy set; Information extraction; Natural language processing; Information retrieval; Data mining; Advertising; Programming language","authors":[{"name":"Ralf Krestel","is_ca":false},{"name":"Sabine Bergler","is_ca":true},{"name":"René Witte","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01539149631651612,"gpt":0.2320307436379919,"spread":0.2166392473214758,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003178984,0.0004943593,0.0004950145,0.001774721,0.0004764566,0.001921382,0.001207176,0.001186386,0.002502699],"category_scores_gemma":[0.01105729,0.0003766397,0.0006846834,0.0005924699,0.0006583535,0.001899598,0.0006680147,0.0007099829,0.0006068844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006487494,"about_ca_system_score_gemma":0.0003487382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003482104,"about_ca_topic_score_gemma":0.003074729,"domain_scores_codex":[0.9983574,0.0008973602,0.0000639302,0.0003674797,0.0002449716,0.00006896384],"domain_scores_gemma":[0.9914575,0.00686009,0.0005712608,0.0004079157,0.0005336907,0.0001696909],"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":[0.001442269,0.001240803,0.1116525,0.0004673465,0.0009458362,0.00161169,0.01202547,0.3615392,0.02582097,0.06562392,0.004946917,0.4126831],"study_design_scores_gemma":[0.00002245392,0.0001228781,0.004173066,0.00001691926,0.00006900403,0.0001303225,0.0005411913,0.9762547,0.001653229,0.01610307,0.000884874,0.00002823764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3882325,0.0003680385,0.602039,0.00136499,0.00002765392,0.0001964113,0.0003769416,0.0008424654,0.006551895],"genre_scores_gemma":[0.9150895,0.00009486881,0.08322735,0.000079086,0.00003595962,0.00005611107,0.0001651204,0.00002129115,0.001230733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003482104,"threshold_uncertainty_score":0.01681226,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388731527","doi":"10.1017/s1351324923000529","title":"Korean named entity recognition based on language-specific features – CORRIGENDUM","year":2023,"lang":"en","type":"erratum","venue":"Natural Language Engineering","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":"University of British Columbia","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Content (measure theory); Natural language processing; Information retrieval; Artificial intelligence; Database; World Wide Web","authors":[{"name":"Yige Chen","is_ca":false},{"name":"KyungTae Lim","is_ca":false},{"name":"Jungyeul Park","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01251648226489134,"gpt":0.2419384875471892,"spread":0.2294220052822979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008945065,0.001088513,0.0008209739,0.001538975,0.000947396,0.002120643,0.001280158,0.001073141,0.07033081],"category_scores_gemma":[0.007221515,0.0004249924,0.0006416319,0.001745249,0.000541109,0.00180399,0.0009291676,0.001408819,0.07174063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001030194,"about_ca_system_score_gemma":0.001078405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01239628,"about_ca_topic_score_gemma":0.01983834,"domain_scores_codex":[0.9992251,0.0001036288,0.0001480923,0.0001415743,0.0003330937,0.00004859775],"domain_scores_gemma":[0.9948537,0.0005056783,0.0001464901,0.0006305784,0.003737837,0.0001258131],"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":[0.00004811326,0.00002003094,0.0001656575,0.0001472049,0.00001650534,0.0006597371,0.00002536788,0.0001824331,0.0008989096,0.001255639,0.9561004,0.04047994],"study_design_scores_gemma":[0.00001890944,0.00003758346,0.002116223,0.0001419429,0.00005504158,0.001108262,0.0001261945,0.002360163,0.005663846,0.002539647,0.9857772,0.00005501493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"other","genre_scores_codex":[0.00818963,0.00768495,0.06627665,0.04189344,0.776669,0.0003066548,0.01526762,0.008511608,0.07520048],"genre_scores_gemma":[0.04932385,0.01089891,0.07350224,0.01769648,0.02871746,0.0002447429,0.0400966,0.005645645,0.773874],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.07033081,"threshold_uncertainty_score":0.23528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2047851837","doi":"10.1017/s1351324901002716","title":"Scalable generation of texts using causal and temporal expansions of sentences","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentence; Artificial intelligence; Natural language processing; Scalability; Kernel (algebra); Process (computing); Theoretical computer science; Information retrieval; Programming language","authors":[{"name":"Yllias Chali","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01503705218098906,"gpt":0.2628490486382299,"spread":0.2478119964572408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00174119,0.0006828542,0.0005216601,0.0008996585,0.0005392498,0.0009581512,0.001279315,0.0005371519,0.00507691],"category_scores_gemma":[0.009235212,0.0004582104,0.0008970586,0.0005578607,0.0007526568,0.002484795,0.001669799,0.0008799948,0.001288698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004043153,"about_ca_system_score_gemma":0.0004738184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007626747,"about_ca_topic_score_gemma":0.001233139,"domain_scores_codex":[0.9986628,0.0004857598,0.0000845305,0.0003033127,0.0004088757,0.0000547542],"domain_scores_gemma":[0.9941606,0.004151512,0.0002458232,0.0008522181,0.0005033643,0.00008648098],"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":[0.0007519955,0.0003047582,0.001710231,0.0006967605,0.0001122883,0.0009818812,0.00198679,0.06566448,0.1069623,0.05280654,0.009141457,0.7588806],"study_design_scores_gemma":[0.0001789417,0.0002699741,0.001348296,0.00007376439,0.0001750722,0.0005812069,0.0003966266,0.8070766,0.09435052,0.06295892,0.03250411,0.00008593037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0289336,0.0001370183,0.9600132,0.0001848124,0.00004192403,0.0002392381,0.0002634941,0.007584094,0.002602574],"genre_scores_gemma":[0.1971669,0.0001405625,0.7973164,0.00008856987,0.00007117372,0.0002408143,0.001179585,0.0008036014,0.002992435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00507691,"threshold_uncertainty_score":0.01698399,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129174913","doi":"10.1017/s1351324908004683","title":"Industry Watch: Language technology, meet social networking","year":2008,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Thread (computing); World Wide Web; Quarter (Canadian coin); Language technology; Data science; Telecommunications; Artificial intelligence; Natural language; Programming language; Comprehension approach; History","authors":[{"name":"Robert Dale","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004611272547601871,"gpt":0.209634801010973,"spread":0.2050235284633712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007179299,0.0007500151,0.0002596133,0.001523128,0.002499793,0.003911814,0.0005639233,0.002249456,0.1732839],"category_scores_gemma":[0.00239146,0.0002420449,0.000335882,0.000988118,0.0003932579,0.005535456,0.002156726,0.002193985,0.09054659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000526891,"about_ca_system_score_gemma":0.0005207997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002330858,"about_ca_topic_score_gemma":0.008295477,"domain_scores_codex":[0.9996872,0.00004415639,0.00001144069,0.00003349925,0.0001359604,0.00008779729],"domain_scores_gemma":[0.9988727,0.0001553,0.00006968733,0.0000540458,0.000186392,0.0006619807],"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":[0.00001686671,0.00001893751,0.0002554276,0.00003765729,0.000002294366,0.00004258333,0.0001415689,0.000007364139,0.0003123881,0.001178311,0.9727272,0.02525931],"study_design_scores_gemma":[0.000007626974,0.00002308988,0.0009680658,0.00003170166,0.000003876821,0.00005864193,0.000647534,0.00007262792,0.0001771155,0.0006534039,0.9973484,0.000007948607],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"commentary","genre_scores_codex":[0.01157026,0.01132414,0.00423214,0.1439588,0.03055168,0.0002184211,0.005436687,0.009862799,0.782845],"genre_scores_gemma":[0.0356392,0.005369115,0.002855218,0.02821578,0.01268101,0.0001776717,0.004563848,0.001772489,0.9087256],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.1732839,"threshold_uncertainty_score":0.5796923,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}