{"id":"W2888353881","doi":"10.1109/icosc.2019.8665531","title":"You Shall Know the Most Frequent Sense by the Company it Keeps","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Identification (biology); Task (project management); Computer science; Sense (electronics); Word (group theory); Translation (biology); Natural language processing; Word-sense disambiguation; Artificial intelligence; Linguistics; Philosophy; Engineering","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":[0.0004743424,0.0004852495,0.0003596427,0.002331563,0.0006054651,0.0009416644,0.0002612762,0.0008067964,0.01011971],"category_scores_gemma":[0.003573134,0.0002329054,0.0002619619,0.002392383,0.0004874796,0.002320973,0.0005165836,0.0005828717,0.006214795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001830221,"about_ca_system_score_gemma":0.0001831544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001364005,"about_ca_topic_score_gemma":0.002355946,"domain_scores_codex":[0.9995036,0.00006280997,0.00005900507,0.0001495561,0.0001815734,0.00004344944],"domain_scores_gemma":[0.998614,0.0005447197,0.0002153164,0.0001685399,0.0003581322,0.00009927815],"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":[0.001206974,0.0002185945,0.0844019,0.001191413,0.0002049634,0.003468667,0.003651763,0.00105304,0.16089,0.03647878,0.1183275,0.5889063],"study_design_scores_gemma":[0.00009297031,0.0006431522,0.2896375,0.0005426048,0.0003137625,0.02293903,0.005742169,0.03362929,0.07327493,0.108766,0.4639196,0.0004987929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.63217,0.004899218,0.2437532,0.0113972,0.003085881,0.000224926,0.03971751,0.005652545,0.05909963],"genre_scores_gemma":[0.8498016,0.001979028,0.1127217,0.0007513334,0.0008786214,0.0001049175,0.01255874,0.0007001441,0.02050397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01011971,"threshold_uncertainty_score":0.03385377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01744385059541804,"score_gpt":0.2732372140732239,"score_spread":0.2557933634778059,"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."}}