{"id":"W2594829673","doi":"10.1016/j.eswa.2017.03.006","title":"Enhanced question understanding with dynamic memory networks for textual question answering","year":2017,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Question answering; Computer science; Artificial intelligence; Dynamic random-access memory; Natural language processing; Information retrieval","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":[0.0008309583,0.0008839921,0.0007458264,0.001512323,0.0006609657,0.001793122,0.001844666,0.001580236,0.01263633],"category_scores_gemma":[0.006743533,0.000397312,0.0006601482,0.00118196,0.0004023853,0.005818244,0.002303153,0.001563424,0.002723923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008858614,"about_ca_system_score_gemma":0.0008351735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00665113,"about_ca_topic_score_gemma":0.009801405,"domain_scores_codex":[0.999453,0.0001252293,0.00003989556,0.0002285908,0.00008585768,0.00006735828],"domain_scores_gemma":[0.99708,0.001890486,0.000162341,0.0004080299,0.0003553416,0.0001036536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007680526,0.0004855346,0.001381745,0.0003802027,0.00009806127,0.000203641,0.0005920544,0.04651222,0.0282365,0.01255683,0.011175,0.8976103],"study_design_scores_gemma":[0.00003181793,0.0001114452,0.0004379608,0.00003643452,0.00006601933,0.00008931188,0.0002135663,0.9436906,0.015639,0.03228863,0.007369714,0.00002558584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06460421,0.001189293,0.9129167,0.0008386078,0.0001785714,0.0002714659,0.00164598,0.01163581,0.006719325],"genre_scores_gemma":[0.6244789,0.000549959,0.3604351,0.0004088125,0.000175234,0.0003139749,0.003344769,0.0005005189,0.00979267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01263633,"threshold_uncertainty_score":0.04227275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02361650187737214,"score_gpt":0.2928168512079417,"score_spread":0.2692003493305696,"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."}}