{"id":"W836999996","doi":"10.18653/v1/w15-4640","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; Samsung Advanced Institute of Technology","keywords":"Computer science; Benchmark (surveying); Dialog box; Microblogging; Task (project management); Artificial intelligence; Natural language processing; Social media; Resource (disambiguation); World Wide Web; Geography","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":[0.00235571,0.002808895,0.001721808,0.003662755,0.002709169,0.002017484,0.002360523,0.003202057,0.00978261],"category_scores_gemma":[0.01084222,0.0006091137,0.0008461811,0.003736521,0.001018721,0.002448204,0.003759555,0.002639217,0.01154458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001850092,"about_ca_system_score_gemma":0.002521742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01616824,"about_ca_topic_score_gemma":0.02628179,"domain_scores_codex":[0.9961128,0.001608575,0.0003620936,0.0006466763,0.0009516288,0.0003181662],"domain_scores_gemma":[0.9946832,0.002143159,0.0002959451,0.001047257,0.001262186,0.0005681357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008545098,0.0007186223,0.002587482,0.002293197,0.0001318855,0.0005035136,0.001181458,0.003618141,0.003720261,0.003277074,0.914489,0.06662489],"study_design_scores_gemma":[0.0007407621,0.0004613312,0.02447262,0.0007863053,0.0001640933,0.001267769,0.002324289,0.05491409,0.01152318,0.009114733,0.8938584,0.0003723099],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0763943,0.01154184,0.02721303,0.002465836,0.002652164,0.001734129,0.83632,0.01996524,0.02171355],"genre_scores_gemma":[0.06674842,0.001083758,0.03041152,0.0004132615,0.0002889941,0.002199695,0.8915497,0.001102677,0.006201903],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01616824,"threshold_uncertainty_score":0.03272611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1752930382556378,"score_gpt":0.3902715041426384,"score_spread":0.2149784658870007,"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."}}