{"id":"W6966556966","doi":"10.48448/zvjr-kz09","title":"Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Alternation (linguistics); Word (group theory); Sentence; Verb; ENCODE","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":[0.001214349,0.001591372,0.0004723157,0.0003741423,0.0003210063,0.001268174,0.001286599,0.00115047,0.005436168],"category_scores_gemma":[0.006873949,0.0005814526,0.0009266523,0.0003102953,0.0005594992,0.004830905,0.001881146,0.002776195,0.003246644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007511174,"about_ca_system_score_gemma":0.0007634782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004080866,"about_ca_topic_score_gemma":0.008705215,"domain_scores_codex":[0.9994166,0.0001631419,0.00003031315,0.0002878551,0.00004668,0.00005548793],"domain_scores_gemma":[0.9978216,0.001230389,0.0001417571,0.0005170016,0.0001525589,0.0001367032],"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":[0.0009876138,0.0006736707,0.0260873,0.0004579727,0.000369101,0.0006029506,0.001154912,0.1457379,0.08426744,0.008025825,0.01438414,0.7172512],"study_design_scores_gemma":[0.00004149848,0.0002189311,0.00471128,0.00003975178,0.00006837227,0.000131187,0.0002865072,0.9511763,0.02426899,0.01568131,0.003341239,0.00003478324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6457413,0.001229947,0.3288988,0.001741422,0.0002150343,0.0001084786,0.002275249,0.01162677,0.008163054],"genre_scores_gemma":[0.9395044,0.0001929444,0.05281215,0.0003319511,0.00003250071,0.00006489807,0.003456284,0.0002850326,0.003319973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005436168,"threshold_uncertainty_score":0.01818585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04520536613552254,"score_gpt":0.3216495426044942,"score_spread":0.2764441764689716,"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."}}