{"id":"W2409591106","doi":"10.18653/v1/d16-1147","title":"Key-Value Memory Networks for Directly Reading Documents","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":204,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Schema (genetic algorithms); Key (lock); Reading (process); Information retrieval; Construct (python library); Benchmark (surveying); Domain (mathematical analysis); Value (mathematics); Artificial intelligence; Machine learning; Programming 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":[0.001329525,0.001461467,0.0008512301,0.002533831,0.000910005,0.002382514,0.002566223,0.001939019,0.007613529],"category_scores_gemma":[0.01264545,0.0006687683,0.0008568122,0.002784895,0.000684279,0.0110791,0.001979135,0.001895256,0.003786633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001539313,"about_ca_system_score_gemma":0.001144662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003885104,"about_ca_topic_score_gemma":0.007077401,"domain_scores_codex":[0.9989462,0.0003152833,0.00008433215,0.0003670737,0.000201922,0.00008517606],"domain_scores_gemma":[0.9941065,0.003784485,0.0003732372,0.001151698,0.0004895244,0.00009447108],"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":[0.0004189123,0.0002184289,0.002765235,0.0008680993,0.0001228425,0.0002222248,0.0009260525,0.07884081,0.01175665,0.0646362,0.04529475,0.7939299],"study_design_scores_gemma":[0.00005429107,0.0000898646,0.00072354,0.0001046475,0.00008432906,0.0002494478,0.0004206053,0.7269357,0.0214144,0.2164011,0.03347404,0.00004797892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03940699,0.002412638,0.9330784,0.001366719,0.0001525086,0.0002398617,0.004185383,0.01063689,0.008520595],"genre_scores_gemma":[0.3377257,0.001437211,0.6338562,0.0004166071,0.0002262785,0.0006390142,0.01101738,0.001266182,0.0134154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007613529,"threshold_uncertainty_score":0.02546984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02520738783624055,"score_gpt":0.2830949033013971,"score_spread":0.2578875154651566,"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."}}