{"id":"W3098382480","doi":"10.1007/978-3-030-63591-6_63","title":"Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection","year":2021,"lang":"en","type":"preprint","venue":"Springer proceedings in mathematics & statistics","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Transformer; Language model; Question answering; Encoder; Selection (genetic algorithm); Sentence; Artificial intelligence; Natural language processing; Task (project management); Machine learning; Voltage","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005951365,0.0003890227,0.0005290516,0.0003228774,0.000173813,0.000688489,0.0006420974,0.0003185573,0.00003176634],"category_scores_gemma":[0.0005492666,0.0004534268,0.0001400059,0.0003100679,0.00004744223,0.0003980472,0.0004118718,0.0007482182,0.000003941158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002937774,"about_ca_system_score_gemma":0.0003491288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001975257,"about_ca_topic_score_gemma":0.0001645435,"domain_scores_codex":[0.9969465,0.00001663697,0.0009378974,0.001044836,0.0005891061,0.0004649979],"domain_scores_gemma":[0.9981679,0.0004025186,0.000403787,0.0002685066,0.0006513141,0.000105924],"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":[0.00005347264,0.00179798,0.008922438,0.01017602,0.001042675,0.00005401815,0.1082536,0.01622342,0.01402287,0.7557104,0.003243404,0.08049977],"study_design_scores_gemma":[0.0003055134,0.00001741381,0.0004183299,0.0004491276,0.00006513972,0.00000700189,0.001147525,0.778181,0.00245609,0.2162262,0.0002760619,0.0004506508],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01990914,0.0001257337,0.9760681,0.0001906535,0.001149759,0.0008536258,0.0001309984,0.000213367,0.001358617],"genre_scores_gemma":[0.07140592,0.0001234844,0.9275126,0.00005016662,0.0002332622,0.0003642458,0.00006970639,0.00005500642,0.0001855745],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7619575,"threshold_uncertainty_score":0.9997917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04253244669200808,"score_gpt":0.306499181081527,"score_spread":0.263966734389519,"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."}}