{"id":"W2160765088","doi":"10.3115/1073427.1073438","title":"Automatically discovering word senses","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Word (group theory); Cluster analysis; Computer science; Artificial intelligence; Natural language processing; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001304596,0.00007255183,0.0000716713,0.00004153457,0.00004967568,0.0001910225,0.0003669042,0.00002920891,0.00003141565],"category_scores_gemma":[0.0001408115,0.00005330986,0.00002467944,0.0002084523,0.00001791068,0.0004390924,0.00009640158,0.00007187723,0.0000318836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000190155,"about_ca_system_score_gemma":0.00003013076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005959773,"about_ca_topic_score_gemma":0.000002435107,"domain_scores_codex":[0.999398,0.0000264176,0.0001002817,0.0001746512,0.0001379258,0.0001627129],"domain_scores_gemma":[0.9995577,0.00004946885,0.00002374692,0.0003013854,0.00002533325,0.00004230686],"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":[2.712935e-7,0.00001235893,0.00006159833,0.000008356494,0.000002267922,0.00001811337,0.0001362414,0.000001285219,0.002728004,0.9587144,0.0004726042,0.03784452],"study_design_scores_gemma":[0.0002044145,0.00005593901,0.0002493963,0.00009796731,0.000005066956,0.000189893,0.00005088414,0.01968731,0.4059297,0.5663502,0.00659188,0.0005873482],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003380502,0.0002381198,0.9789267,0.0003155306,0.00007486186,0.00004603069,8.490988e-8,0.0013159,0.01570228],"genre_scores_gemma":[0.3771598,0.000001235278,0.6219599,0.0002593377,0.000005858445,0.000002277972,7.05199e-8,0.000002996655,0.0006085358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4032018,"threshold_uncertainty_score":0.2173913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009390139955483549,"score_gpt":0.2565597385996673,"score_spread":0.2471695986441838,"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."}}