{"id":"W4386566695","doi":"10.18653/v1/2023.eacl-main.206","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Conversation; Computer science; Task (project management); Table (database); Set (abstract data type); Data set; Information retrieval; Data science; Natural language processing; Artificial intelligence; Data mining; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000430608,0.00008224144,0.00007860178,0.00002895348,0.0002967233,0.0002628106,0.002060416,0.00001890306,0.00001482645],"category_scores_gemma":[0.0001418869,0.00004961398,0.000007961476,0.0005342842,0.0000562537,0.001001055,0.001426138,0.00009159091,0.00009536595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002062361,"about_ca_system_score_gemma":0.0000832691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009734601,"about_ca_topic_score_gemma":0.001251835,"domain_scores_codex":[0.9989043,0.00003774302,0.0001599147,0.0003847579,0.0002562311,0.0002570382],"domain_scores_gemma":[0.9976594,0.0002316471,0.00005150435,0.001969867,0.00004564059,0.00004192777],"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":[0.00002334302,0.00005959902,0.007285108,0.0000451726,0.0002147493,0.00009170361,0.004367297,0.003081194,0.0003078616,0.2926091,0.6262634,0.06565151],"study_design_scores_gemma":[0.0003132577,0.00003217394,0.0009469513,0.00002522054,0.0000111506,0.000007972373,0.0006430175,0.725123,0.0001566427,0.003041025,0.2695087,0.0001908389],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002098113,0.00006287052,0.9898726,0.00611812,0.0003122158,0.0001568474,0.0005966193,0.0002365334,0.0005460528],"genre_scores_gemma":[0.7546541,0.0008531713,0.2256441,0.003246606,0.0003704224,0.00004172071,0.01190276,0.00004854011,0.003238593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7642285,"threshold_uncertainty_score":0.38288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1111507670832012,"score_gpt":0.3048785513780047,"score_spread":0.1937277842948034,"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."}}