{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184013,0.001111649,0.001268594,0.001164129,0.0007437989,0.001255154,0.001542164,0.00101357,0.002413826],"category_scores_gemma":[0.004931001,0.001068926,0.002879567,0.001210825,0.0007716623,0.001932257,0.002123986,0.002745103,0.003364632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000533251,"about_ca_system_score_gemma":0.001055875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005633029,"about_ca_topic_score_gemma":0.008635009,"domain_scores_codex":[0.9985519,0.0006498906,0.00007083453,0.0003611293,0.0002453713,0.00012092],"domain_scores_gemma":[0.9982084,0.0009500099,0.00008027991,0.0003082158,0.0003824641,0.00007055859],"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":[0.0009079603,0.0003819986,0.002262029,0.0002325029,0.0006280156,0.0001969008,0.0005612398,0.3597555,0.03579842,0.01854072,0.007999299,0.5727355],"study_design_scores_gemma":[0.00001261602,0.0000187964,0.0003695641,0.000008078599,0.00003167092,0.00004291176,0.00002189303,0.9910203,0.002677583,0.004779932,0.0009929822,0.00002367569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006576063,0.0002061521,0.9914766,0.00008261784,0.00006183459,0.00002824942,0.000091083,0.001042209,0.0004350829],"genre_scores_gemma":[0.3764825,0.0008077711,0.6100355,0.0002731248,0.0002516129,0.0004505574,0.002507906,0.001755212,0.007435794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005633029,"threshold_uncertainty_score":0.01120049,"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."}}