{"id":"W889023230","doi":"10.1609/aaai.v30i1.9883","title":"Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models","year":2016,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Generative grammar; Computer science; Bootstrapping (finance); Word (group theory); Artificial intelligence; Language model; Domain (mathematical analysis); Encoder; Artificial neural network; Recurrent neural network; Task (project management); Natural language processing; Generative model; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001900789,0.0009429394,0.0009059009,0.0004499903,0.0006188741,0.001392328,0.001696429,0.001531424,0.003092678],"category_scores_gemma":[0.006887283,0.0008231837,0.001090377,0.0003485489,0.0008849495,0.003022382,0.002318599,0.002151133,0.002295271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008334301,"about_ca_system_score_gemma":0.0008417488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00289495,"about_ca_topic_score_gemma":0.004640866,"domain_scores_codex":[0.9988331,0.0004775123,0.00005003416,0.0004224344,0.0001350138,0.0000819214],"domain_scores_gemma":[0.9975249,0.001663382,0.0001082863,0.0002735271,0.0002953269,0.0001344871],"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":[0.0004266137,0.0004064415,0.001658424,0.0003758493,0.0002484299,0.0005450995,0.001682814,0.7262614,0.03592732,0.02776014,0.005268332,0.1994391],"study_design_scores_gemma":[0.000009768892,0.0000225626,0.00005992852,0.000005812348,0.00001123612,0.00002034709,0.00003056626,0.98999,0.002556877,0.006625056,0.0006591359,0.000008665908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03055936,0.0001700492,0.9620315,0.0001902148,0.00006205645,0.0001038616,0.0001407174,0.004925826,0.001816357],"genre_scores_gemma":[0.5969196,0.0001778022,0.3952686,0.0003063127,0.00006049784,0.0003943414,0.0009611749,0.0005833046,0.005328402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003092678,"threshold_uncertainty_score":0.01034606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1601300793042809,"score_gpt":0.3229457412957319,"score_spread":0.1628156619914511,"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."}}