{"id":"W3159905742","doi":"10.48550/arxiv.2010.11140","title":"A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Leverage (statistics); Computer science; Exploit; Transformer; Labeled data; Artificial intelligence; Natural language processing; Multi-task learning; Task (project management); Language model; 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":[0.004444974,0.002474191,0.001761254,0.001159904,0.000837421,0.001212418,0.003779284,0.002418759,0.008487855],"category_scores_gemma":[0.009963264,0.000875095,0.001837954,0.001052945,0.0009505334,0.003162372,0.003506433,0.004238855,0.005255118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009440203,"about_ca_system_score_gemma":0.002319815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00234203,"about_ca_topic_score_gemma":0.004317633,"domain_scores_codex":[0.9963421,0.001736969,0.0001527967,0.001105228,0.0004081859,0.0002547317],"domain_scores_gemma":[0.9937715,0.003712089,0.000241467,0.000934773,0.0009893905,0.0003507643],"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":[0.001354429,0.001070126,0.001567491,0.0005519292,0.0002487458,0.000238996,0.000520267,0.11081,0.03758771,0.007349441,0.01791164,0.8207892],"study_design_scores_gemma":[0.00009473045,0.0001938406,0.0004503135,0.00001589777,0.00004412203,0.00009264287,0.00008059551,0.9767082,0.008911936,0.01052169,0.00284156,0.00004445943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007878359,0.0003207939,0.9843739,0.0002122894,0.0001236593,0.0002525364,0.0003002129,0.005336212,0.001202096],"genre_scores_gemma":[0.3840983,0.0002526894,0.6009375,0.0006867173,0.0003347966,0.001346031,0.003333017,0.0009261246,0.008084742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008487855,"threshold_uncertainty_score":0.0283947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.140993043562373,"score_gpt":0.2072054085802734,"score_spread":0.06621236501790043,"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."}}