{"id":"W4307680525","doi":"10.1162/tacl_a_00545","title":"Generative Spoken Dialogue Language Modeling","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Paralanguage; Computer science; Transformer; Spoken language; Generative grammar; Speech recognition; Natural language processing; Laughter; Language model; Artificial intelligence; Communication; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003788576,0.00007701094,0.00011996,0.0001190965,0.0002667954,0.00004750771,0.0003206098,0.00005777039,0.000006401258],"category_scores_gemma":[0.001192981,0.00006874448,0.0001683919,0.000494014,0.00001309841,0.00004848591,0.00001499508,0.00007721843,0.00002637584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009084,"about_ca_system_score_gemma":0.00009153716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001834511,"about_ca_topic_score_gemma":0.00001283945,"domain_scores_codex":[0.9990723,0.00005804852,0.0002562591,0.0001463827,0.0003277204,0.0001392757],"domain_scores_gemma":[0.9981995,0.0007700344,0.0001624226,0.0001479935,0.0006903863,0.00002961352],"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":[0.000005890661,0.00005781431,0.0001247061,0.00001692951,0.0001034115,4.349561e-7,0.000975523,0.9443718,0.00009044241,0.04926354,0.0007801335,0.004209383],"study_design_scores_gemma":[0.0002326306,0.0000136682,0.0003395423,0.00000975468,0.00002707672,5.019593e-7,0.00006681948,0.9604092,0.0008483696,0.03725531,0.0007157958,0.00008129659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00261978,0.000008111875,0.9939814,0.0007426671,0.001041246,0.0001927447,0.0002275426,0.0001530527,0.001033427],"genre_scores_gemma":[0.896062,0.000004492444,0.1025423,0.0001129742,0.000162364,0.00002720898,0.00005087228,0.000009641694,0.001028244],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8934422,"threshold_uncertainty_score":0.2803318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03106876500409547,"score_gpt":0.2777580017736145,"score_spread":0.246689236769519,"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."}}