{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001919653,0.0001372304,0.0001448906,0.00005152759,0.0005608985,0.00100408,0.001931852,0.00005986746,0.000312054],"category_scores_gemma":[0.0001405006,0.0001197791,0.00007006402,0.00004623592,0.00003509182,0.0009540911,0.001012928,0.0001372553,0.0005094474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000258194,"about_ca_system_score_gemma":0.00007136699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001143583,"about_ca_topic_score_gemma":0.0001091725,"domain_scores_codex":[0.99862,0.00002355504,0.0001993603,0.000449578,0.0003028369,0.000404658],"domain_scores_gemma":[0.99805,0.00005210206,0.000112862,0.001628422,0.00005795312,0.0000986884],"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":[0.00001915052,0.00006818213,0.01294414,0.00002994405,0.00003801002,0.00028641,0.001220372,0.002053256,0.004225859,0.607654,0.003962581,0.3674981],"study_design_scores_gemma":[0.0004794158,0.00008085143,0.01438083,0.00001521966,0.000006199646,0.0001032331,0.00005469545,0.9233654,0.01232455,0.03838137,0.01036922,0.0004390005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5718251,0.00001528741,0.3207538,0.004647936,0.0006563871,0.0001420457,0.000001035747,0.0003120616,0.1016464],"genre_scores_gemma":[0.9681885,0.000001251735,0.02274343,0.002796838,0.0001745933,0.000004991071,4.872331e-7,0.00001019299,0.006079671],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9213122,"threshold_uncertainty_score":0.968237,"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."}}