{"id":"W2050369426","doi":"10.3115/1118735.1118737","title":"Induction of classification from lexicon expansion","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Academia Sinica; National Science Council","keywords":"WordNet; Computer science; Natural language processing; Lexicon; Artificial intelligence; Categorization; Information retrieval; Taxonomy (biology); Semantic similarity; Hierarchy; Lexical database","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":[0.00005698615,0.00004664513,0.0000584755,0.00006206929,0.00002524678,0.00002924871,0.000305494,0.0000549359,0.00007548925],"category_scores_gemma":[0.00002464545,0.0000377296,0.00001770434,0.0001954185,0.0000172581,0.0004803932,0.00005357671,0.00006322708,0.00002034608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001729742,"about_ca_system_score_gemma":0.000005954378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007788641,"about_ca_topic_score_gemma":0.000003001933,"domain_scores_codex":[0.9995052,0.00001981581,0.0001194236,0.0001625963,0.0001323459,0.00006057872],"domain_scores_gemma":[0.9995416,0.00002015691,0.00007418935,0.0002910935,0.00005507948,0.00001783789],"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":[0.000001036738,0.00004147008,0.0001219338,0.000004403897,0.00000233894,6.329455e-7,0.0004339622,4.206887e-7,0.4339094,0.08715014,0.001674763,0.4766594],"study_design_scores_gemma":[0.00009933626,0.0000412106,0.001266838,0.0000270191,0.000002448171,0.000002616471,0.0000314499,0.05670465,0.8616008,0.07977755,0.0003374502,0.0001086249],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04557549,0.0007482566,0.9495378,0.001102822,0.0001264851,0.00006208602,5.331931e-7,0.0004984952,0.002348038],"genre_scores_gemma":[0.6390023,0.00001020612,0.3607676,0.00005341784,0.00001793198,0.000002071991,0.000001175798,0.000001771621,0.0001434797],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5934268,"threshold_uncertainty_score":0.1538568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04685674669557996,"score_gpt":0.2699579955299167,"score_spread":0.2231012488343368,"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."}}