{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01770778,0.0008047831,0.0008554155,0.002360029,0.001457047,0.004374564,0.001501435,0.00301483,0.003672172],"category_scores_gemma":[0.1575872,0.001063291,0.0009038812,0.001695947,0.00972139,0.02055125,0.007441875,0.004185596,0.0005945196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008443543,"about_ca_system_score_gemma":0.001013801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002744324,"about_ca_topic_score_gemma":0.00222173,"domain_scores_codex":[0.9858233,0.007331509,0.001019955,0.003252103,0.001970146,0.0006031002],"domain_scores_gemma":[0.823885,0.1283156,0.009478915,0.03186782,0.005165632,0.001286998],"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":[0.001164211,0.0001962216,0.09247816,0.001367884,0.0003306801,0.001895563,0.09534524,0.008657454,0.09258183,0.331601,0.003748655,0.3706331],"study_design_scores_gemma":[0.00009497158,0.000458174,0.06359819,0.0006802791,0.0002378615,0.00363967,0.01755364,0.05877855,0.05367806,0.778119,0.02279424,0.0003674849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5466878,0.001292896,0.4154182,0.006872431,0.0001088342,0.0002233841,0.0005232123,0.001267049,0.02760614],"genre_scores_gemma":[0.9582821,0.0001893404,0.03985268,0.0004695962,0.00003519712,0.00007630565,0.0002788072,0.0001758368,0.0006401445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01770778,"threshold_uncertainty_score":0.09364879,"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."}}