{"id":"W4283720480","doi":"10.1007/s10115-022-01703-7","title":"BertHANK: hierarchical attention networks with enhanced knowledge and pre-trained model for answer selection","year":2022,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence; Machine learning; Model selection","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":[0.0004929884,0.0001322438,0.0001707524,0.0001648278,0.0004598118,0.0002025723,0.0001663717,0.00005990408,0.000001292301],"category_scores_gemma":[0.0000105143,0.000117309,0.0000294686,0.0002687054,0.00002096438,0.001849061,0.0001437316,0.0001467328,0.000002274312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006966907,"about_ca_system_score_gemma":0.00008487309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007558683,"about_ca_topic_score_gemma":0.00001331407,"domain_scores_codex":[0.9989871,0.00007177509,0.0003634077,0.0002164091,0.0001450169,0.0002162591],"domain_scores_gemma":[0.9993695,0.00005619978,0.0001351446,0.0001671541,0.0001912443,0.00008074818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003041245,0.0002048765,0.001068215,0.001087109,0.0001301147,3.827309e-7,0.06253926,0.4906362,0.0007432767,0.2002124,0.002936682,0.2401374],"study_design_scores_gemma":[0.000781659,0.0001763212,0.0003218305,0.00003053991,0.000008502134,0.00002751618,0.0001391786,0.9896848,0.00002146335,0.00009569195,0.008555933,0.000156535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0325024,0.0004255946,0.9637461,0.00005641778,0.0003869177,0.0006977399,0.000005698295,0.0001226451,0.002056487],"genre_scores_gemma":[0.9948586,0.00001834797,0.003514121,0.00004365548,0.0001152898,0.0004240689,0.00003607832,0.000007154095,0.0009826896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9623562,"threshold_uncertainty_score":0.4783724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01161435937029967,"score_gpt":0.2366141620126121,"score_spread":0.2249998026423124,"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."}}