{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001750964,0.0009003184,0.00102181,0.001855123,0.0005288039,0.002082696,0.001362778,0.001172308,0.01040065],"category_scores_gemma":[0.01109329,0.0005043648,0.0009363997,0.001899525,0.0006206412,0.004873977,0.002303175,0.001877566,0.003812177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00074982,"about_ca_system_score_gemma":0.001714524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002497115,"about_ca_topic_score_gemma":0.004764995,"domain_scores_codex":[0.9986805,0.0004718105,0.0000954887,0.0002753377,0.0003015411,0.0001752267],"domain_scores_gemma":[0.9952349,0.00304555,0.0001558799,0.0006901008,0.0007072548,0.0001663421],"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":[0.001265801,0.0003230164,0.001877935,0.0004455635,0.0001085605,0.0002483963,0.0004615144,0.02576195,0.01780543,0.1458972,0.03198013,0.7738246],"study_design_scores_gemma":[0.0001093088,0.0001320524,0.0003333063,0.00007210454,0.000107635,0.0001119799,0.0001739262,0.6968089,0.01490688,0.2783422,0.008863607,0.00003804044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02008777,0.0004285005,0.9679501,0.0005735507,0.0001966038,0.0001316727,0.001619244,0.005849952,0.003162635],"genre_scores_gemma":[0.6066667,0.0007239473,0.3774535,0.0003820639,0.0003675937,0.0003557394,0.006694316,0.001153492,0.006202726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01040065,"threshold_uncertainty_score":0.03479367,"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."}}