{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001404219,0.000074351,0.00007023377,0.00005933734,0.00006709907,0.00004569663,0.0003706996,0.0000351816,0.00002850625],"category_scores_gemma":[0.00001083507,0.00006661588,0.0000307351,0.0001225581,0.000007491346,0.0004691764,0.0001164575,0.00005896653,0.00001870405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002205327,"about_ca_system_score_gemma":0.00004056275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000402197,"about_ca_topic_score_gemma":0.00002301265,"domain_scores_codex":[0.9992959,0.00001995482,0.0001437127,0.0002282462,0.000136992,0.0001752247],"domain_scores_gemma":[0.9995213,0.00001147563,0.00003426333,0.0003482387,0.00003594574,0.00004874366],"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":[0.000006500024,0.0001111134,0.0007665546,0.00002952621,0.0000243417,0.0000350238,0.08565441,0.1594479,0.02053648,0.5054628,0.00003372884,0.2278916],"study_design_scores_gemma":[0.00009984614,0.000006338924,0.00003823216,0.000006617396,0.000002409001,0.000003615186,0.0002963427,0.9928455,0.002793788,0.003811294,0.000003308226,0.00009265732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2006387,0.00002237555,0.7877676,0.00002343612,0.00007031898,0.00004936576,1.38313e-7,0.000188375,0.0112396],"genre_scores_gemma":[0.5171196,4.74638e-7,0.4826315,0.0001039914,0.00001594334,0.000001161083,2.31361e-7,0.000003506961,0.0001235062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8333977,"threshold_uncertainty_score":0.2716517,"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."}}