{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001047871,0.00007259459,0.00009932827,0.00006051513,0.0001073753,0.0001691194,0.0001398793,0.00004263002,0.00001628771],"category_scores_gemma":[0.00003222205,0.00006500463,0.00003104565,0.000183469,0.00003569574,0.0003728133,0.0002841045,0.00008575186,0.000006449949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001050297,"about_ca_system_score_gemma":0.00004467207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000246552,"about_ca_topic_score_gemma":0.00005891529,"domain_scores_codex":[0.9993713,0.00003385339,0.0001106655,0.0002626508,0.00006294495,0.0001585304],"domain_scores_gemma":[0.9996087,0.00008828386,0.00002394746,0.0001865328,0.00004014383,0.00005236831],"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":[0.0000179853,0.0003091899,0.01440077,0.0001876154,0.00009980072,0.0004107935,0.003510806,0.0004698407,0.09911699,0.2578263,0.001353372,0.6222966],"study_design_scores_gemma":[0.0005296648,0.00004601604,0.0139814,0.00006829308,0.00001659477,0.001070681,0.0004178584,0.9192494,0.02830001,0.006303319,0.02958058,0.0004361543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1358859,0.0003206289,0.8544488,0.0002633969,0.0002945271,0.00004139623,8.009211e-8,0.00008941822,0.008655908],"genre_scores_gemma":[0.7284815,0.00002375744,0.2710504,0.0001055938,0.00004802113,0.000003764121,2.448623e-7,0.0000029362,0.0002838361],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9187796,"threshold_uncertainty_score":0.2650812,"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."}}