{"id":"W3159836094","doi":"10.1145/3412841.3441959","title":"Taxonomy extraction using knowledge graph embeddings and hierarchical clustering","year":2021,"lang":"en","type":"article","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Axiom; Cluster analysis; Knowledge graph; Taxonomy (biology); Semantic Web; Information retrieval; Graph; Knowledge extraction; Entity linking; Hierarchical clustering; Information extraction; Artificial intelligence; Data mining; Theoretical computer science; Natural language processing; Knowledge base; Mathematics","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":[0.001304953,0.00112145,0.0007732276,0.008702223,0.001171068,0.002158696,0.001276918,0.001269371,0.001908667],"category_scores_gemma":[0.009383823,0.0006222486,0.001630194,0.007098216,0.000603865,0.004737558,0.002030102,0.001448735,0.001660794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001132827,"about_ca_system_score_gemma":0.002083208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007138617,"about_ca_topic_score_gemma":0.01946345,"domain_scores_codex":[0.9978827,0.0004641443,0.0002437985,0.0006109141,0.0006783718,0.0001200431],"domain_scores_gemma":[0.9956366,0.001534684,0.0004442749,0.0009562125,0.001302029,0.0001262488],"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":[0.0001328832,0.0003213925,0.00993053,0.001024276,0.0003417141,0.0005588675,0.001230048,0.03314521,0.02031195,0.05133855,0.02486088,0.8568037],"study_design_scores_gemma":[0.00005037835,0.00009741317,0.00581466,0.000314399,0.0002108035,0.0009182461,0.001363472,0.753791,0.02376739,0.1571919,0.0563737,0.0001064818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01658252,0.0003530552,0.9745701,0.0002347783,0.00006014065,0.0003027261,0.00217091,0.003583345,0.002142429],"genre_scores_gemma":[0.05597707,0.0002143779,0.9360861,0.00006401023,0.00001518779,0.0001683838,0.006200961,0.0002082167,0.001065685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008702223,"threshold_uncertainty_score":0.01419413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06141243123416966,"score_gpt":0.3051442174310978,"score_spread":0.2437317861969281,"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."}}