{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003963672,0.002439726,0.001664782,0.001116414,0.0007581901,0.001120794,0.003591653,0.002226613,0.008526886],"category_scores_gemma":[0.008665948,0.0008127801,0.001720541,0.0009783417,0.0008675205,0.003100211,0.003228137,0.003976353,0.005063317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008664779,"about_ca_system_score_gemma":0.002207049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002297737,"about_ca_topic_score_gemma":0.004304443,"domain_scores_codex":[0.9969077,0.001374302,0.0001328778,0.0009678401,0.0003809449,0.0002363708],"domain_scores_gemma":[0.9946911,0.00305874,0.0002184309,0.0008000921,0.0009262462,0.0003054644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00122964,0.0009881315,0.001347572,0.0005051271,0.0002236557,0.0002224216,0.0004646448,0.09317053,0.04236869,0.005871814,0.0155078,0.8381],"study_design_scores_gemma":[0.0001023787,0.0002239732,0.0004863948,0.00001592369,0.00004807405,0.0001010234,0.00008858774,0.9757887,0.01106703,0.008928621,0.003101869,0.00004748905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008690195,0.0003448815,0.9826134,0.000190178,0.0001226678,0.0002618009,0.0002845526,0.006222315,0.001270038],"genre_scores_gemma":[0.393094,0.0002601156,0.5922577,0.000654348,0.0002933982,0.001262491,0.003132959,0.0009083448,0.008136626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008526886,"threshold_uncertainty_score":0.02852529,"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."}}