{"id":"W2593751037","doi":"10.5087/dad.2017.102","title":"Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus","year":2017,"lang":"en","type":"article","venue":"Dialogue & Discourse","topic":"Topic Modeling","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; Samsung Advanced Institute of Technology","keywords":"Utterance; Computer science; Conversation; Context (archaeology); Task (project management); Artificial intelligence; Construct (python library); Natural language processing; Feature engineering; End-to-end principle; Recall; Feature (linguistics); Precision and recall; Artificial neural network; Speech recognition; Machine learning; Deep learning; 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":[0.003414104,0.002785882,0.001183196,0.000911732,0.001030879,0.001691567,0.002644169,0.002213203,0.006716634],"category_scores_gemma":[0.01076533,0.0008683479,0.001143383,0.0006272497,0.000728379,0.002875923,0.002183222,0.003433058,0.005764708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001702836,"about_ca_system_score_gemma":0.001276737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01146266,"about_ca_topic_score_gemma":0.01610716,"domain_scores_codex":[0.9972655,0.001205978,0.0001251044,0.0009867853,0.000228228,0.0001884951],"domain_scores_gemma":[0.9962167,0.002160238,0.000109801,0.0005528635,0.0007625284,0.0001978241],"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":[0.002551694,0.002400896,0.00637616,0.001488684,0.0007249638,0.0007614478,0.002447007,0.3314799,0.02358606,0.003604995,0.07930416,0.5452741],"study_design_scores_gemma":[0.0001818157,0.0004252322,0.002023577,0.00008931271,0.00009030511,0.0001504169,0.0004735979,0.9620607,0.01693306,0.002981755,0.01450958,0.00008068801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3880969,0.004139055,0.47181,0.001303586,0.002074148,0.002080805,0.012063,0.09972835,0.01870414],"genre_scores_gemma":[0.5913557,0.0005424359,0.3553995,0.0008249721,0.0001891324,0.00226195,0.03220155,0.002263123,0.01496169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01146266,"threshold_uncertainty_score":0.02279186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04910393159180949,"score_gpt":0.2845377901034271,"score_spread":0.2354338585116176,"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."}}