{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00123295,0.0006768814,0.0008704629,0.0002880137,0.0004123285,0.001190938,0.005297609,0.0004082618,0.00001549778],"category_scores_gemma":[0.000341561,0.0004942476,0.0003098193,0.0005826528,0.0003270273,0.0005637904,0.004680851,0.00124734,0.00002048342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002607259,"about_ca_system_score_gemma":0.0004375208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002462331,"about_ca_topic_score_gemma":0.00001011785,"domain_scores_codex":[0.9948056,0.0001149067,0.001334434,0.001649283,0.001130495,0.0009652257],"domain_scores_gemma":[0.9964831,0.0002484889,0.0009470956,0.0009552878,0.001064974,0.0003010012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002913205,0.00003302315,0.00001836435,0.00006487429,0.00003101249,0.000001350466,0.0008473984,0.2870162,0.01056561,0.6804513,0.00003619968,0.02090557],"study_design_scores_gemma":[0.00001472418,0.0000495498,0.00000356339,0.0009028941,0.00001748076,0.000006465358,0.00003835648,0.5953829,0.01782551,0.3854041,0.00001441589,0.0003401159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.112661,0.000100329,0.8778299,0.002767324,0.003596584,0.001130103,0.00002837181,0.0001664015,0.001719986],"genre_scores_gemma":[0.9313929,0.00002325667,0.06695736,0.0002581679,0.001160207,0.00009722599,9.218734e-7,0.00004160939,0.0000683589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8187319,"threshold_uncertainty_score":0.9998459,"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."}}