{"id":"W2132551194","doi":"10.1109/ccece.2011.6030578","title":"Unsupervised language model adaptation using n-gram weighting","year":2011,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Latent Dirichlet allocation; Perplexity; Language model; Computer science; Weighting; Topic model; n-gram; Artificial intelligence; Cluster analysis; Vocabulary; Document clustering; Natural language processing; Word (group theory); Mathematics; Linguistics","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":[0.001753679,0.0009901668,0.0009100917,0.0009156844,0.0004609731,0.0008243584,0.001148413,0.0006816832,0.001428468],"category_scores_gemma":[0.005373215,0.0003865009,0.001202163,0.00103285,0.0003962619,0.001768131,0.001264464,0.001545364,0.001768198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004060252,"about_ca_system_score_gemma":0.0006787828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002691481,"about_ca_topic_score_gemma":0.003846187,"domain_scores_codex":[0.9982958,0.0007885583,0.00007449387,0.0004118143,0.0003426927,0.00008658203],"domain_scores_gemma":[0.9984999,0.0007381947,0.00009557163,0.0002975902,0.0003250996,0.00004371784],"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":[0.0003628081,0.0004049367,0.002309338,0.0002225518,0.0004120245,0.0002394914,0.0005231812,0.1665707,0.06555813,0.01438724,0.005975281,0.7430344],"study_design_scores_gemma":[0.00001458458,0.00005718098,0.0008136715,0.00001193269,0.00004940053,0.0001223878,0.00004508538,0.9750767,0.01022531,0.00911876,0.004424237,0.00004076805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008692216,0.0001887025,0.9890627,0.00005146356,0.00006139501,0.00006466407,0.00005501918,0.001201024,0.0006226714],"genre_scores_gemma":[0.3013324,0.0006928996,0.6882727,0.000288069,0.0002055135,0.0006072218,0.001446209,0.001151146,0.006003813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002691481,"threshold_uncertainty_score":0.009274423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1257445697567923,"score_gpt":0.2653257100981551,"score_spread":0.1395811403413628,"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."}}