{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001518833,0.0002821792,0.0003364006,0.0001034817,0.00007553299,0.0003031316,0.0007346654,0.0001828637,0.000005236426],"category_scores_gemma":[0.000008069169,0.0002173252,0.00004021517,0.0001088234,0.00004644335,0.0003906115,0.001944204,0.0007501623,0.0000033603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003140701,"about_ca_system_score_gemma":0.00007665434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005638269,"about_ca_topic_score_gemma":0.0004455352,"domain_scores_codex":[0.9982333,0.00004762805,0.000235517,0.0008493463,0.0002822327,0.0003519883],"domain_scores_gemma":[0.998819,0.00007704201,0.00007573664,0.0008596212,0.00004508421,0.0001235297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007364481,0.000007830173,0.0001436327,0.0001212022,0.00006444065,0.0001577141,0.004637316,0.8961426,0.00001905333,0.08164354,0.00008632126,0.01696897],"study_design_scores_gemma":[0.0001609675,0.00001877607,0.000180979,0.0001087442,0.00001223732,0.00002433185,0.0003331202,0.9866608,0.00003769644,0.01216378,0.000004436662,0.0002940783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1589091,0.000290799,0.8390222,0.0003200572,0.0004768038,0.0001975012,0.000002176368,0.0005060643,0.0002752678],"genre_scores_gemma":[0.9690052,0.00007326528,0.03009352,0.0001447718,0.0002387464,0.00003141941,0.00000969089,0.0000293208,0.0003740991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8100961,"threshold_uncertainty_score":0.8862266,"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."}}