{"id":"W4321012596","doi":"10.18653/v1/2023.eacl-main.167","title":"Exploring Category Structure with Contextual Language Models and Lexical Semantic Networks","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Computer science; Natural language processing; Artificial intelligence; WordNet; Polysemy; Similarity (geometry); Task (project management); Word (group theory); Semantic similarity; Priming (agriculture); Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001432219,0.0009565964,0.0006367053,0.002392184,0.0004607743,0.001598214,0.000756643,0.000876851,0.002587802],"category_scores_gemma":[0.007405586,0.0004270971,0.0009460368,0.001834778,0.0005998302,0.005272653,0.001222661,0.001404974,0.0008988061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007204744,"about_ca_system_score_gemma":0.0005795167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003715665,"about_ca_topic_score_gemma":0.007636516,"domain_scores_codex":[0.9994123,0.0002852988,0.00002589267,0.0001860514,0.00004662979,0.00004391783],"domain_scores_gemma":[0.9966167,0.002395537,0.0002765653,0.0003604355,0.0002109089,0.0001399071],"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":[0.001137371,0.0005648335,0.0877152,0.000703616,0.0007363024,0.00044458,0.001920193,0.3770366,0.01421283,0.09454048,0.00817838,0.4128096],"study_design_scores_gemma":[0.00001526955,0.00006199301,0.004020795,0.00003045848,0.00004323182,0.00008839929,0.0001671043,0.8539672,0.0008355051,0.1390554,0.001691577,0.00002304325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3864646,0.001571533,0.603706,0.0008056216,0.00008845301,0.00006088396,0.001566519,0.001231321,0.00450511],"genre_scores_gemma":[0.9301559,0.0003486446,0.0667959,0.00010285,0.00006258727,0.00007283239,0.001406439,0.00009958769,0.0009552088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003715665,"threshold_uncertainty_score":0.008657038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1242877977873987,"score_gpt":0.2696044762852646,"score_spread":0.1453166784978659,"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."}}