{"id":"W2155313075","doi":"10.1109/wi.2007.37","title":"Automatic Taxonomy Extraction Using Google and Term Dependency","year":2007,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Terminology; Dependency (UML); Taxonomy (biology); Data mining; Adjacency matrix; Information extraction; Information retrieval; Term (time); Adjacency list; Formal concept analysis; Artificial intelligence; Theoretical computer science; Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000975199,0.001315084,0.001415801,0.02502122,0.001648742,0.001837954,0.001113669,0.0009594218,0.002547891],"category_scores_gemma":[0.00650187,0.0006330488,0.001671366,0.01719924,0.0003265316,0.003718657,0.001877152,0.0007866173,0.002598213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234735,"about_ca_system_score_gemma":0.003553659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009261054,"about_ca_topic_score_gemma":0.01607547,"domain_scores_codex":[0.9981588,0.0002170865,0.0002211831,0.0003123003,0.0009677894,0.0001229659],"domain_scores_gemma":[0.9973505,0.0008089057,0.0003095267,0.0002496246,0.001183186,0.00009829633],"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":[0.0001941259,0.0001998962,0.006915802,0.001588839,0.0002625872,0.0009337681,0.0009187001,0.007005883,0.0302384,0.0237364,0.04956498,0.8784406],"study_design_scores_gemma":[0.0001292779,0.0002187693,0.02628581,0.0007323401,0.0005213597,0.004334554,0.001868475,0.5474687,0.06126885,0.1093577,0.247422,0.0003920685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05040755,0.002589654,0.8946,0.0007226497,0.0002453082,0.00118914,0.01968816,0.02171772,0.008839798],"genre_scores_gemma":[0.082479,0.001187691,0.8850597,0.00008473905,0.00006228727,0.0007035738,0.02716792,0.0004494983,0.002805645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02502122,"threshold_uncertainty_score":0.01841426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03794426146626626,"score_gpt":0.3148330309274555,"score_spread":0.2768887694611892,"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."}}