{"id":"W3170012708","doi":"10.18653/v1/2021.naacl-main.392","title":"A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Leverage (statistics); Transformer; Exploit; Artificial intelligence; Natural language processing; Labeled data; Multi-task learning; Task (project management); Language model; Text generation; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001476929,0.0000542893,0.00007176833,0.00002492576,0.0001566913,0.0001209033,0.00008092204,0.00002993992,0.000004493377],"category_scores_gemma":[0.00006629792,0.00005143708,0.00002258854,0.00007393057,0.000008954022,0.00008364201,0.00008597915,0.00004522347,0.000001698578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001332473,"about_ca_system_score_gemma":0.00003131352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000118963,"about_ca_topic_score_gemma":0.000008679624,"domain_scores_codex":[0.9993699,0.00003829493,0.0001059881,0.000290227,0.00007671476,0.0001189076],"domain_scores_gemma":[0.9996766,0.00003995817,0.00002560675,0.0001492209,0.00007028332,0.00003837052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002400491,0.0001764429,0.0006592255,0.00004709657,0.00002341119,0.000005408083,0.002208679,0.7823548,0.06304495,0.122441,0.0003894304,0.02864719],"study_design_scores_gemma":[0.0003631975,0.00001268903,0.0001620392,9.802521e-7,0.000002488826,0.000005630147,0.00004715594,0.9945179,0.004271679,0.0001470092,0.0004000186,0.00006920374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0587722,0.00005541618,0.9405893,0.0001133904,0.00006718782,0.0001281664,0.000001466194,0.00007169588,0.0002011865],"genre_scores_gemma":[0.6366722,0.000001338645,0.362873,0.0001251332,0.00004554258,0.00002424923,0.00004715392,0.000002609937,0.0002087906],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5779001,"threshold_uncertainty_score":0.2097543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05191918823681962,"score_gpt":0.2668601196632878,"score_spread":0.2149409314264682,"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."}}