{"id":"W4206165639","doi":"10.1145/775107.775138","title":"Discovering word senses from text","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Word (group theory); Computer science; Cluster analysis; Precision and recall; Set (abstract data type); Artificial intelligence; Similarity (geometry); Centroid; Natural language processing; Feature (linguistics); Feature vector; Element (criminal law); Space (punctuation); Cluster (spacecraft); Domain (mathematical analysis); Information retrieval; Mathematics; Linguistics; Image (mathematics)","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":[0.00003268549,0.00007709526,0.00007211565,0.00003867755,0.00005049497,0.000212412,0.0005379531,0.00003228089,0.0002037743],"category_scores_gemma":[0.00002854806,0.00005841106,0.00002609644,0.0001744265,0.0000163987,0.0005640503,0.0002338457,0.00008485845,0.0001304213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001791556,"about_ca_system_score_gemma":0.000003317144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001388103,"about_ca_topic_score_gemma":0.00001409987,"domain_scores_codex":[0.9994053,0.00001217516,0.00008532764,0.0002223773,0.0001319077,0.0001429158],"domain_scores_gemma":[0.9995236,0.00005168991,0.00002691197,0.0003448596,0.00001656896,0.00003636378],"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":[0.00000136366,0.00004655933,0.0004181805,0.000007084052,0.0000103747,0.00008254681,0.001491535,0.000003523915,0.01386092,0.05488569,0.01291042,0.9162818],"study_design_scores_gemma":[0.0005045414,0.00008976293,0.001091932,0.0002307919,0.00001275967,0.00007035657,0.000129091,0.1866325,0.553677,0.230154,0.02601708,0.00139016],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01982188,0.00260279,0.9652413,0.001358657,0.0001408841,0.00005190093,0.000001184718,0.001544218,0.009237207],"genre_scores_gemma":[0.5288298,0.00001006614,0.4694398,0.0003201117,0.00003631744,0.000001645298,3.067987e-7,0.00000339955,0.001358555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9148917,"threshold_uncertainty_score":0.2381934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01633319923786609,"score_gpt":0.2386434594540469,"score_spread":0.2223102602161808,"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."}}