{"id":"W3179689435","doi":"","title":"A Joint Model for Question Answering and Question Generation","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Novelty; Question answering; Artificial intelligence; Generative model; Comprehension; Perspective (graphical); Generative grammar; Joint (building); Sequence (biology); Natural language processing; Ask price; Sequence labeling; Machine learning; Programming language; Task (project management); Engineering","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":[0.0004593256,0.0001079292,0.000095807,0.00009173002,0.0004037026,0.0007029136,0.0004103738,0.0000486003,0.0000068737],"category_scores_gemma":[0.0003610164,0.0001087081,0.00003086704,0.00001183246,0.0000217936,0.0006688396,0.0001533847,0.0001894386,0.000004692186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005117695,"about_ca_system_score_gemma":0.00003534603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001304902,"about_ca_topic_score_gemma":0.00006584855,"domain_scores_codex":[0.999116,0.00004091179,0.000172139,0.0003441168,0.0002045483,0.0001222626],"domain_scores_gemma":[0.9993178,0.00002100006,0.0001844853,0.0002533699,0.0001776761,0.00004566476],"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":[0.00001067069,0.00001319239,0.001410552,0.000007264685,0.00001006966,0.000001524336,0.0003223849,0.08453503,0.01105219,0.8080654,0.000008803696,0.09456294],"study_design_scores_gemma":[0.0002730303,0.0000500742,0.001138261,0.00005712078,0.000002542041,0.000005444955,0.000004700941,0.9838834,0.0004672139,0.01386977,0.0001341147,0.0001142794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05306012,0.00001554166,0.9400303,0.004554648,0.0003672252,0.0001138601,0.000002578581,0.00008895418,0.001766718],"genre_scores_gemma":[0.926003,0.00003232566,0.07281577,0.0001113712,0.0001724825,0.00002657153,0.00001674496,0.000007539435,0.0008141756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8993484,"threshold_uncertainty_score":0.6778212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1139660243069028,"score_gpt":0.3511012088271431,"score_spread":0.2371351845202403,"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."}}