{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009462133,0.000169077,0.0001625585,0.00008898678,0.0006118687,0.000593917,0.002587507,0.00008323483,0.000004072102],"category_scores_gemma":[0.0007189938,0.0001395886,0.00006231225,0.000176177,0.0001119112,0.0008041844,0.0004644339,0.0001996996,0.00002482648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006755932,"about_ca_system_score_gemma":0.00004696631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001157597,"about_ca_topic_score_gemma":0.00007541651,"domain_scores_codex":[0.9983215,0.00004257341,0.0004207655,0.0005790071,0.0003558529,0.0002802461],"domain_scores_gemma":[0.9981098,0.00004163643,0.000424782,0.0007943807,0.0005083551,0.0001210507],"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":[0.0001773291,0.0001043291,0.0002280326,0.000006971975,0.000003982524,1.871357e-7,0.001182061,0.01040385,0.1013495,0.366076,0.00004866024,0.5204192],"study_design_scores_gemma":[0.00001883247,0.0001651938,0.001182767,0.00003961818,0.000004047732,0.000001247101,0.00004793328,0.9146518,0.07581438,0.007888355,0.00004040901,0.0001453985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4039633,0.000005617022,0.5903889,0.004283138,0.0006320092,0.0004555787,0.000001717633,0.00006333456,0.0002064069],"genre_scores_gemma":[0.9926512,0.000007059806,0.006783692,0.0001838402,0.000261935,0.00006962319,9.940254e-7,0.000008803581,0.00003281967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9042479,"threshold_uncertainty_score":0.5727155,"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."}}