{"id":"W2810821963","doi":"10.5087/dad.2018.101","title":"A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version","year":2018,"lang":"en","type":"article","venue":"Dialogue & Discourse","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; McGill University; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Samsung; Compute Canada; Samsung Advanced Institute of Technology; Canadian Institute for Advanced Research","keywords":"Computer science; Data science; Artificial intelligence; Transfer of learning; Data-driven; Machine learning","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":[0.01904847,0.001600518,0.00181157,0.01331458,0.002428056,0.005478545,0.004737551,0.002323529,0.0225133],"category_scores_gemma":[0.07938923,0.001766904,0.001252764,0.020189,0.002087669,0.008500996,0.004769988,0.003153273,0.01947124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002173811,"about_ca_system_score_gemma":0.005698648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004336862,"about_ca_topic_score_gemma":0.00698217,"domain_scores_codex":[0.9837266,0.006142931,0.002886008,0.00244566,0.004495636,0.0003031339],"domain_scores_gemma":[0.9107084,0.05425183,0.002561713,0.01602809,0.01496953,0.001480414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003436968,0.0003408582,0.005636648,0.01343121,0.0001785682,0.0002491913,0.001480244,0.004159671,0.005432594,0.01890762,0.28477,0.6650697],"study_design_scores_gemma":[0.00005931632,0.0001053178,0.008137676,0.003353654,0.0000783337,0.0004989677,0.000664529,0.004785548,0.008292857,0.0106902,0.963172,0.0001615235],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"review","genre_scores_codex":[0.02742877,0.0972506,0.3525999,0.009356732,0.00515734,0.002649438,0.3970071,0.03043065,0.07811948],"genre_scores_gemma":[0.04081134,0.02607972,0.3749047,0.001495632,0.0009167872,0.003671796,0.5349616,0.007889258,0.00926917],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.0225133,"threshold_uncertainty_score":0.1007391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0922818192006133,"score_gpt":0.3122704740781831,"score_spread":0.2199886548775699,"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."}}