{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001769218,0.00006834621,0.00006404998,0.0000263908,0.00005309918,0.00001283741,0.00004808824,0.000125271,0.0000500664],"category_scores_gemma":[0.00004926246,0.00005651152,0.00002212616,0.00003247831,0.00006686514,0.000002003384,0.00004045145,0.00004577005,0.000004067504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007084949,"about_ca_system_score_gemma":0.00001947674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000023243,"about_ca_topic_score_gemma":0.00003846824,"domain_scores_codex":[0.9995157,0.00001073268,0.0001146009,0.0001563651,0.00005373696,0.0001489288],"domain_scores_gemma":[0.9997715,0.0000140724,0.00003532495,0.0001057782,0.00001431907,0.00005895031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001154309,0.00003102557,0.0110178,0.00001566693,0.00001836053,0.000007048241,0.00001475392,4.824008e-7,0.495179,0.00003164253,0.000316333,0.4933564],"study_design_scores_gemma":[0.001543005,0.0006960972,0.1545224,0.00006242938,0.00007703587,0.0007331271,0.001152103,0.003024467,0.6978748,0.0004327277,0.1390658,0.0008159569],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9294044,0.0003958374,0.06721783,0.00003507052,0.00009386383,0.00006559634,6.739866e-7,0.00002231494,0.002764429],"genre_scores_gemma":[0.9670753,0.00002954953,0.03229469,0.00008974178,0.0001023307,0.000002992944,0.000005807396,0.000005443287,0.0003941221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4925404,"threshold_uncertainty_score":0.2304473,"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."}}