{"id":"W2626154462","doi":"10.18653/v1/k17-1028","title":"Making Neural QA as Simple as Possible but not Simpler","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Simple (philosophy); Artificial intelligence; Task (project management); Artificial neural network; Context (archaeology); Question answering; Heuristic; Baseline (sea); Perspective (graphical); Machine learning; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003851965,0.0006534166,0.0009035371,0.0006556576,0.0007563024,0.002797138,0.001812965,0.001830125,0.006695984],"category_scores_gemma":[0.01728744,0.000519885,0.0006536451,0.0007154929,0.001082739,0.008910659,0.00219697,0.003280374,0.004318256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008220499,"about_ca_system_score_gemma":0.001014279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003172586,"about_ca_topic_score_gemma":0.005133856,"domain_scores_codex":[0.9983575,0.0006401676,0.00009554132,0.0005658224,0.0002479465,0.00009309165],"domain_scores_gemma":[0.9937192,0.003005367,0.0002694041,0.001854295,0.0009770448,0.0001746928],"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":[0.0006456325,0.0003860649,0.004444199,0.001299026,0.000287463,0.0001889201,0.001054316,0.09095102,0.05997955,0.07843065,0.03071289,0.7316203],"study_design_scores_gemma":[0.00006818474,0.0002526959,0.002187304,0.0001266888,0.000122492,0.0002680382,0.0002946314,0.7623734,0.02880186,0.1771449,0.02829911,0.00006075122],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08181901,0.002041447,0.8833885,0.004600189,0.0003520885,0.0002266064,0.001039968,0.01353258,0.01299969],"genre_scores_gemma":[0.5667455,0.001084081,0.4183668,0.001540551,0.0002911148,0.0002724834,0.003068322,0.0006164528,0.008014816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006695984,"threshold_uncertainty_score":0.02240032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09895202575389195,"score_gpt":0.3529582687877168,"score_spread":0.2540062430338249,"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."}}