{"id":"W3113945743","doi":"10.18653/v1/2020.semeval-1.76","title":"TR at SemEval-2020 Task 4: Exploring the Limits of Language-model-based Common Sense Validation","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Commonsense knowledge; SemEval; Concreteness; Language model; Natural language processing; Commonsense reasoning; Task (project management); Artificial intelligence; Embedding; Knowledge graph; Language understanding; Common sense; Domain knowledge; Cognitive psychology; Psychology","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":[0.0500135,0.004635816,0.002617896,0.002682322,0.003058673,0.007613399,0.007308445,0.007604038,0.01452843],"category_scores_gemma":[0.1735328,0.001128471,0.002624807,0.00159544,0.003169897,0.01438568,0.01256177,0.01003066,0.01077176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002951848,"about_ca_system_score_gemma":0.005004996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01112931,"about_ca_topic_score_gemma":0.0160168,"domain_scores_codex":[0.9463859,0.03791442,0.002007897,0.007152085,0.005073199,0.001466551],"domain_scores_gemma":[0.8050822,0.1357817,0.003102205,0.03236105,0.01901052,0.004662351],"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":[0.004860937,0.002679275,0.0130637,0.003874447,0.001490053,0.001098593,0.004912411,0.05180548,0.02016328,0.01659295,0.4346012,0.4448577],"study_design_scores_gemma":[0.00251447,0.001983768,0.009885616,0.001167301,0.0004393173,0.001648917,0.004788653,0.6652326,0.04346962,0.106445,0.1616845,0.0007403281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3447109,0.009099332,0.4330403,0.02100757,0.009367794,0.003187404,0.03657091,0.08741638,0.05559934],"genre_scores_gemma":[0.6482306,0.000507142,0.2381511,0.004930436,0.000955341,0.001977561,0.08165769,0.0100623,0.01352778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0500135,"threshold_uncertainty_score":0.2644998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09066099485163504,"score_gpt":0.2827639114547911,"score_spread":0.1921029166031561,"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."}}