{"id":"W3103735191","doi":"10.18653/v1/2020.eval4nlp-1.11","title":"Grammaticality and Language Modelling","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grammaticality; Variable (mathematics); Computer science; Language model; Correlation; Natural language processing; Linguistics; Artificial intelligence; Cola (plant); Point (geometry); Psychology; Cognitive psychology; Grammar; Mathematics","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":[0.00007177251,0.00004755162,0.00006067592,0.00001112744,0.00002768282,0.0001024281,0.0002642703,0.00002281645,0.000006553489],"category_scores_gemma":[0.00003079441,0.00003591061,0.00001114106,0.0001111464,0.00001533046,0.0002246722,0.0001735595,0.00007260164,0.000007337891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003337489,"about_ca_system_score_gemma":0.000006587893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001680293,"about_ca_topic_score_gemma":4.56388e-7,"domain_scores_codex":[0.9995885,0.00001304693,0.00006913999,0.0001593038,0.00008420893,0.00008573342],"domain_scores_gemma":[0.999752,0.00002308388,0.00001456041,0.0001224973,0.00001458217,0.00007327949],"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":[0.000002228524,0.000009694348,0.00005458201,0.00006584114,0.000004310194,0.00002952972,0.003976174,0.00002994195,0.00384585,0.8998134,0.0004254805,0.09174296],"study_design_scores_gemma":[0.00004840048,0.0000166584,0.000002661881,0.000005049766,0.000001290197,0.000004628043,0.00003208026,0.9196172,0.01842457,0.06159542,0.0001650477,0.00008700458],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002908375,0.0006563301,0.9904774,0.004379628,0.000007532267,0.00003833864,1.883887e-7,0.0007271838,0.0008049692],"genre_scores_gemma":[0.4456449,0.000002029605,0.5532137,0.00110842,0.00001112993,8.149843e-7,1.717564e-7,0.000001501042,0.0000173784],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9195873,"threshold_uncertainty_score":0.1464392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02606263882137646,"score_gpt":0.2678293875160296,"score_spread":0.2417667486946531,"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."}}