{"id":"W2809215328","doi":"10.1109/compsac.2018.00113","title":"Long Short-Term Memory Neural Networks for Artificial Dialogue Generation","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Hidden Markov model; Encoder; Artificial neural network; Artificial intelligence; Sequence (biology); Recurrent neural network; Term (time); Decoding methods; Long short term memory; Architecture; Speech recognition; Natural language processing; Algorithm","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":[0.0002854268,0.0001177083,0.0001322336,0.00005712847,0.0002005925,0.000259566,0.0004020182,0.00008622834,0.00001709316],"category_scores_gemma":[0.00002910363,0.0001005129,0.00007576856,0.000156579,0.00004890901,0.0003645751,0.00008394178,0.00004950617,0.00004452361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002269046,"about_ca_system_score_gemma":0.00003041324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004725591,"about_ca_topic_score_gemma":0.000977776,"domain_scores_codex":[0.9988827,0.00004568806,0.0002431489,0.0003549845,0.0001439136,0.000329571],"domain_scores_gemma":[0.9992845,0.00005164832,0.0000403229,0.0003976335,0.0001221785,0.0001036991],"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":[0.0001248744,0.00023171,0.006814008,0.00003339462,0.00007699258,0.00004415447,0.001450816,0.00387786,0.03349831,0.07792532,0.07735096,0.7985716],"study_design_scores_gemma":[0.0001324211,0.0001782897,0.001591652,0.000002640186,0.000004657226,0.00001217218,0.000006540612,0.9843302,0.01299107,0.0004319432,0.0001473967,0.0001709886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0788975,0.00003393564,0.9145521,0.0001995763,0.004405342,0.0003445234,0.000001775591,0.0001771585,0.001388075],"genre_scores_gemma":[0.9866622,6.935413e-7,0.006050424,0.0003948166,0.006567802,0.00004487546,0.00003560782,0.000009138556,0.0002344248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9804524,"threshold_uncertainty_score":0.4098796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05047732032030343,"score_gpt":0.2742333457109574,"score_spread":0.2237560253906539,"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."}}