{"id":"W3105864207","doi":"10.18653/v1/2020.emnlp-main.71","title":"Word class flexibility: A deep contextualized approach","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Vector Institute; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Flexibility (engineering); Computer science; Class (philosophy); Noun; Verb; Word (group theory); Natural language processing; Linguistics; Artificial intelligence; Part of speech; Variation (astronomy); Linguistic typology; Typology; Phenomenon; Mathematics; Sociology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008489022,0.0006436583,0.0005910593,0.001957016,0.0007912397,0.002134066,0.001145298,0.0009869457,0.003657434],"category_scores_gemma":[0.00478815,0.000613822,0.001043771,0.001708274,0.001998676,0.004899976,0.002908408,0.001968393,0.0005801274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001031145,"about_ca_system_score_gemma":0.0007522237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003520373,"about_ca_topic_score_gemma":0.006280232,"domain_scores_codex":[0.999182,0.0002897215,0.00004950514,0.0003124592,0.0000794489,0.00008678095],"domain_scores_gemma":[0.9977775,0.0009647254,0.0003059541,0.0006424934,0.0001966683,0.0001126868],"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":[0.0005323134,0.0003152586,0.0364541,0.0004760962,0.0003047016,0.0006988084,0.005590982,0.1642649,0.01905554,0.3731907,0.004796132,0.3943205],"study_design_scores_gemma":[0.00001722819,0.00007570378,0.005380719,0.00006360438,0.00005865213,0.0001943606,0.0008490421,0.5164456,0.002103584,0.4677798,0.006983444,0.0000483349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.144153,0.0004443135,0.8477634,0.0007228094,0.00005718436,0.00009608294,0.000966138,0.0008840136,0.00491314],"genre_scores_gemma":[0.8189198,0.0002324994,0.1778722,0.0001786205,0.00004792472,0.0001928067,0.0009057727,0.0002127497,0.001437634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003657434,"threshold_uncertainty_score":0.01223534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04017475278434007,"score_gpt":0.286791765619195,"score_spread":0.2466170128348549,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}