{"id":"W2124602574","doi":"10.1145/502512.502558","title":"Induction of semantic classes from natural language text","year":2001,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Set (abstract data type); Task (project management); Space (punctuation); Natural language; Unsupervised learning; Information retrieval","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":[0.00003998731,0.00005338231,0.00007602148,0.00004060989,0.00003120541,0.00003721633,0.0003256657,0.00002802016,0.00009020674],"category_scores_gemma":[0.00001112803,0.00003832421,0.00002275197,0.0001630043,0.00001423342,0.0004723307,0.0001690551,0.00006379592,0.00003838448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006941635,"about_ca_system_score_gemma":0.00001207336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008024178,"about_ca_topic_score_gemma":0.00003780917,"domain_scores_codex":[0.9994952,0.00001722804,0.0001012414,0.0001591352,0.0001390975,0.00008806238],"domain_scores_gemma":[0.9995514,0.00003555012,0.00004223362,0.0003188968,0.00002676434,0.00002520991],"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":[0.00001292255,0.0001556417,0.003650177,0.00001031633,0.00002748543,0.00004901901,0.001300375,0.00002894044,0.1006851,0.009348195,0.009354208,0.8753776],"study_design_scores_gemma":[0.001388422,0.0001838595,0.195807,0.0001540126,0.00002159165,0.00008282068,0.001234292,0.6602108,0.109305,0.006212696,0.02469066,0.0007089264],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6291516,0.0004592318,0.3671739,0.0002686324,0.0005050724,0.00004401263,0.000002735481,0.0001026375,0.002292144],"genre_scores_gemma":[0.9619918,0.00001965484,0.03722697,0.00008063487,0.00008092372,7.870721e-7,0.00001026064,0.00000229316,0.0005866075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8746687,"threshold_uncertainty_score":0.1562816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01160689930725286,"score_gpt":0.2518886837407619,"score_spread":0.240281784433509,"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."}}