{"id":"W3110879614","doi":"","title":"On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT","year":2020,"lang":"en","type":"article","venue":"Joint Conference on Lexical and Computational Semantics","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McGill University","funders":"","keywords":"Computer science; Competence (human resources); Noun; ENCODE; Consistency (knowledge bases); Natural language processing; Artificial intelligence; Cognitive science; Linguistics; Psychology; Philosophy","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":[0.0002825242,0.00008567585,0.0002197848,0.00003304462,0.00007212171,0.00004986383,0.0002287677,0.00002952503,0.000008244991],"category_scores_gemma":[0.0002856322,0.00004850953,0.000044184,0.0001804408,0.00009673601,0.00006113606,0.0001116478,0.0001487523,0.000002633015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008328544,"about_ca_system_score_gemma":0.00005482776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006036516,"about_ca_topic_score_gemma":0.0000112229,"domain_scores_codex":[0.9988565,0.0001768424,0.0004406197,0.0001999345,0.0002373595,0.00008870724],"domain_scores_gemma":[0.9985338,0.0009378226,0.0001790661,0.0001793281,0.0001310151,0.0000389356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001331835,0.00004820488,0.00006580687,0.00008938926,0.00001178964,0.00002196096,0.002237324,0.01439903,0.0000966722,0.9810705,0.00002223941,0.001923713],"study_design_scores_gemma":[0.0002413051,0.00007327734,0.0008585243,0.0002042217,0.000004868411,0.00002941165,0.0005687514,0.9070968,0.0001455072,0.09072142,0.000002162684,0.00005374836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5484113,0.00001791001,0.4269053,0.02382866,0.00003346033,0.000330718,0.000003825316,0.0000142594,0.0004546557],"genre_scores_gemma":[0.9946083,0.000002898079,0.004491682,0.0008608242,0.00001406383,0.00001097563,7.834997e-7,0.000002426466,0.000007987011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8926978,"threshold_uncertainty_score":0.1978161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1101873326005088,"score_gpt":0.2956192324816643,"score_spread":0.1854318998811555,"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."}}