{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004623198,0.0002612032,0.0004819451,0.000161952,0.0005470355,0.000341679,0.003608588,0.0001304116,0.00001881211],"category_scores_gemma":[0.0009138499,0.000180441,0.0001073633,0.0005110091,0.0003925552,0.0009949551,0.0007188857,0.0002042478,0.0002571709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006922433,"about_ca_system_score_gemma":0.0005447465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004178867,"about_ca_topic_score_gemma":0.0009681028,"domain_scores_codex":[0.9969236,0.0007038455,0.0006666672,0.0005346086,0.0005624383,0.0006088432],"domain_scores_gemma":[0.9954908,0.0009364714,0.0006883302,0.001978982,0.0006863755,0.0002190566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005660157,0.0004874321,0.0244496,0.0001990149,0.0003847211,0.00004091101,0.002782328,0.0006728536,0.004599904,0.01390465,0.9467317,0.005180878],"study_design_scores_gemma":[0.01720171,0.006876771,0.07971319,0.002195639,0.0009924405,0.001096255,0.003658966,0.7074451,0.008149116,0.005855404,0.1621881,0.004627287],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1606131,0.003275977,0.8090252,0.0007000808,0.01861139,0.002399863,0.003483182,0.0002316516,0.001659596],"genre_scores_gemma":[0.9949079,0.00006972826,0.003040174,0.00008340998,0.001250331,0.00002233536,0.0004609952,0.00002871975,0.0001363677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8342949,"threshold_uncertainty_score":0.735817,"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."}}