{"id":"W2973459423","doi":"10.48550/arxiv.1909.08187","title":"Learning to Generate Questions with Adaptive Copying Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Copying; Computer science; Artificial intelligence; Component (thermodynamics); Artificial neural network; Recurrent neural network; Natural language processing; Natural language generation; Machine learning; Natural language","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":[0.001504966,0.0008186646,0.000586658,0.0006562615,0.0002737019,0.0007217044,0.001626635,0.001336895,0.002268958],"category_scores_gemma":[0.006822268,0.0003694334,0.000873294,0.0005318431,0.0006112794,0.002505765,0.001228107,0.001393296,0.0009143789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006363507,"about_ca_system_score_gemma":0.0004243082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001829346,"about_ca_topic_score_gemma":0.002493949,"domain_scores_codex":[0.9992009,0.0003205203,0.00004592561,0.0002618699,0.000116506,0.0000542853],"domain_scores_gemma":[0.9973121,0.001783557,0.0002040184,0.0003124982,0.0003081796,0.00007974926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005965809,0.0002853296,0.003726503,0.0004019263,0.0001748889,0.0004163801,0.0007441515,0.228858,0.05742785,0.01380326,0.00784002,0.6857251],"study_design_scores_gemma":[0.0000235046,0.00008524344,0.0004764592,0.00001000861,0.0000279887,0.00007207144,0.00003082891,0.9776977,0.008796069,0.01134043,0.00142496,0.00001480066],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08981547,0.0009336778,0.9008445,0.0005430233,0.0001263936,0.0002175015,0.00035002,0.00461214,0.002557314],"genre_scores_gemma":[0.7841588,0.0004279098,0.2067078,0.0003953865,0.0001390511,0.0003879989,0.001315206,0.0002994793,0.006168236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002268958,"threshold_uncertainty_score":0.007959127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06812994601911321,"score_gpt":0.1844140685608704,"score_spread":0.1162841225417572,"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."}}