{"id":"W4385573423","doi":"10.18653/v1/2022.findings-emnlp.73","title":"MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Sampling","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Fundamental Research Funds for the Central Universities; Ministry of Education, India; Renmin University of China; National Natural Science Foundation of China","keywords":"Computer science; Leverage (statistics); Utterance; Artificial intelligence; Dialog box; Encoder; Focus (optics); Natural language processing; Machine learning; Speech recognition; World Wide Web","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":[0.0004632805,0.0001810917,0.0002420774,0.00008236912,0.0005067332,0.0001136181,0.0007112148,0.00003142449,0.0000728294],"category_scores_gemma":[0.00003811779,0.000158915,0.00007927873,0.0002075203,0.00002341543,0.000294008,0.0002960101,0.0001697463,0.000002091846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001085204,"about_ca_system_score_gemma":0.0002115969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004207966,"about_ca_topic_score_gemma":0.00001881439,"domain_scores_codex":[0.9982976,0.00006284914,0.0002261189,0.0005972421,0.0003692425,0.0004469308],"domain_scores_gemma":[0.9990991,0.0002570765,0.00008360795,0.000347975,0.0001057241,0.0001065267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006139042,0.0009056851,0.002307388,0.0002140598,0.0007590816,0.00006060808,0.2215436,0.05804007,0.008643888,0.4057263,0.0003850447,0.3008004],"study_design_scores_gemma":[0.002946742,0.0001763167,0.0007808375,0.00001443221,0.00001460598,0.00002992934,0.001901556,0.9910896,0.0001220459,0.0003191326,0.00232157,0.0002831922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02568479,0.00005702058,0.9719667,0.0006615445,0.0002038156,0.0006917316,0.00002021012,0.0004269861,0.0002872336],"genre_scores_gemma":[0.3418385,9.435421e-7,0.6562524,0.0005958902,0.00004799911,0.0002649322,0.000005167658,0.00001539773,0.0009788285],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9330496,"threshold_uncertainty_score":0.6480365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1359157354290594,"score_gpt":0.3056195345867609,"score_spread":0.1697037991577015,"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."}}