{"id":"W2047032662","doi":"10.3115/1072228.1072372","title":"Concept discovery from text","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"WordNet; Cluster analysis; Computer science; Set (abstract data type); Centroid; Cluster (spacecraft); Task (project management); Similarity (geometry); Artificial intelligence; Data mining; Feature vector; Information retrieval; Quality (philosophy); Natural language processing; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002704496,0.00007007958,0.0000680903,0.00002801961,0.00004061543,0.0002637395,0.0007213054,0.00003741334,0.0003020871],"category_scores_gemma":[0.0000234143,0.00005162782,0.00002754927,0.0001388492,0.00002802035,0.001033785,0.0001915929,0.00008301948,0.0001395999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001519518,"about_ca_system_score_gemma":0.000004625468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009908029,"about_ca_topic_score_gemma":0.000004132762,"domain_scores_codex":[0.9994227,0.0000144801,0.00008329029,0.0002192365,0.0001327758,0.0001274729],"domain_scores_gemma":[0.9995113,0.0000496922,0.0000276246,0.0003598554,0.00001897045,0.00003254268],"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":[8.228016e-7,0.00006991387,0.0003344562,0.000003365713,0.00001262364,0.00005348034,0.001373081,0.000001203063,0.006566299,0.436032,0.09747782,0.4580749],"study_design_scores_gemma":[0.0005767868,0.0001039869,0.0006433922,0.00007867305,0.000009568,0.00002900572,0.00006094595,0.07911126,0.4711688,0.4189467,0.02825066,0.001020182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001124977,0.003770772,0.9841385,0.001597742,0.0001222096,0.00004450028,0.000001992146,0.0009283478,0.008270969],"genre_scores_gemma":[0.5486988,0.000006535706,0.4459203,0.001113557,0.00004406805,0.000002341417,8.650004e-7,0.000003144303,0.004210358],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5475739,"threshold_uncertainty_score":0.3307642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01340747817539674,"score_gpt":0.2381662981531921,"score_spread":0.2247588199777953,"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."}}