{"id":"W2418993857","doi":"10.1609/aaai.v31i1.10984","title":"Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Margin (machine learning); Recurrent neural network; Sequence (biology); Artificial intelligence; Semantics (computer science); Representation (politics); Artificial neural network; Abstraction; Machine learning; Process (computing); Natural language processing","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":[0.001388168,0.0008621636,0.0006533443,0.0005031097,0.0002323051,0.0007236731,0.001264146,0.001001679,0.001993024],"category_scores_gemma":[0.004518589,0.0004424291,0.0007739615,0.0005547595,0.0003758835,0.001266571,0.000815781,0.001373612,0.0006132079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006753828,"about_ca_system_score_gemma":0.0003984287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004032126,"about_ca_topic_score_gemma":0.004539559,"domain_scores_codex":[0.9993842,0.0002761349,0.00002834441,0.0001417483,0.0001231363,0.00004637521],"domain_scores_gemma":[0.9988686,0.0007271959,0.0001079413,0.000119628,0.0001353911,0.00004120419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002368302,0.0001434958,0.0009158442,0.0001645728,0.0001146492,0.0002728406,0.0003274122,0.7749389,0.0166466,0.01505801,0.002866158,0.1883146],"study_design_scores_gemma":[0.000004105736,0.00001647762,0.00005462988,0.000003344718,0.000006412528,0.00001515867,0.000004165317,0.9965417,0.0009340644,0.002045588,0.0003699774,0.000004391177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02482048,0.0005921496,0.969738,0.0003215423,0.00006074532,0.00006486763,0.0001483172,0.002410334,0.001843579],"genre_scores_gemma":[0.650272,0.0005071396,0.3441286,0.000244064,0.00008808017,0.0002106624,0.0004206918,0.0002756844,0.003852978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004032126,"threshold_uncertainty_score":0.008017302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1386857976164667,"score_gpt":0.3393223618512201,"score_spread":0.2006365642347535,"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."}}