{"id":"W2058080055","doi":"10.1016/j.csl.2014.06.002","title":"Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Artificial intelligence; Language model; Topic model; Probabilistic latent semantic analysis; Pattern recognition (psychology); Scaling; Mixture model; Cluster analysis; Machine learning; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004272985,0.0003056928,0.0003491209,0.0002604329,0.0001465503,0.0003408065,0.0005837039,0.0001342699,0.00003968252],"category_scores_gemma":[0.00002350365,0.000280422,0.0001222509,0.0002965355,0.00004503669,0.0005199662,0.000204978,0.0001837359,0.00003225568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004672932,"about_ca_system_score_gemma":0.00005900077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000908458,"about_ca_topic_score_gemma":0.00002958907,"domain_scores_codex":[0.9980686,0.0001830902,0.0003124738,0.000624863,0.0004031143,0.0004079059],"domain_scores_gemma":[0.9987664,0.0001251216,0.0001208544,0.0006835813,0.0001063256,0.0001976788],"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":[0.00002118374,0.0001672592,0.00006820081,0.0001359585,0.00005131261,0.0002249132,0.007279256,0.06652021,0.008417365,0.003206565,0.0003218655,0.9135859],"study_design_scores_gemma":[0.0006655754,0.00004619325,0.0001361575,0.00008171263,0.0000257883,0.0000601082,0.00009136996,0.9906916,0.006590789,0.001212368,0.00004104834,0.0003573095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2351529,0.0002309916,0.7632119,0.0003533243,0.0001508816,0.0002005862,0.000007039787,0.0002740278,0.0004183405],"genre_scores_gemma":[0.525066,0.000005278073,0.4734133,0.001278925,0.0001158824,0.000005736436,0.00001300831,0.00002165865,0.00008023864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9241714,"threshold_uncertainty_score":0.9999648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03687698171248772,"score_gpt":0.2563463042773522,"score_spread":0.2194693225648645,"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."}}