{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00111718,0.0004780178,0.0005832046,0.000142347,0.001404515,0.001690528,0.004141407,0.0001545617,0.0000102787],"category_scores_gemma":[0.0002458954,0.0003203997,0.0001599603,0.000195555,0.0004761444,0.001032404,0.0007690885,0.0004860547,0.0002638794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009129618,"about_ca_system_score_gemma":0.00035024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00206125,"about_ca_topic_score_gemma":0.001556118,"domain_scores_codex":[0.9964452,0.0002417209,0.0004564002,0.001042482,0.0007882403,0.001025982],"domain_scores_gemma":[0.995326,0.0003108428,0.0004459081,0.003379375,0.0001357563,0.0004021407],"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":[0.0001864557,0.0005406156,0.007474265,0.000161103,0.0005897449,0.001392424,0.0734109,0.02811074,0.00174041,0.4742866,0.01363012,0.3984766],"study_design_scores_gemma":[0.02065594,0.004601195,0.137545,0.003879573,0.001647622,0.002188765,0.01911703,0.4039995,0.003179015,0.02680059,0.3593859,0.01699985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1710307,0.0007280683,0.7834511,0.01568747,0.008089296,0.002048363,0.0002333963,0.0006387923,0.01809273],"genre_scores_gemma":[0.9948337,0.00002004163,0.00236007,0.0006402971,0.001378024,0.0002223366,0.00003881034,0.00005371404,0.0004529726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.823803,"threshold_uncertainty_score":0.9999248,"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."}}