{"id":"W2159863202","doi":"10.1007/s10994-005-0928-7","title":"Combining Statistical Language Models via the Latent Maximum Entropy Principle","year":2005,"lang":"en","type":"article","venue":"Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Computer science; Principle of maximum entropy; Perplexity; Language model; Artificial intelligence; Probabilistic latent semantic analysis; Probabilistic logic; Smoothing; Natural language processing; Inference; Statistical model; Entropy (arrow of time); Natural language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004464366,0.001102938,0.001881184,0.002027558,0.0006836707,0.002868794,0.001616999,0.00152684,0.002288891],"category_scores_gemma":[0.01529936,0.001144235,0.001934154,0.001775671,0.001009969,0.006234653,0.003158675,0.00250711,0.001347047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006254775,"about_ca_system_score_gemma":0.0009795434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001341794,"about_ca_topic_score_gemma":0.002002048,"domain_scores_codex":[0.9966496,0.002078809,0.0001381862,0.0003684065,0.0006019158,0.0001631081],"domain_scores_gemma":[0.9903244,0.008121315,0.0003137414,0.0006224879,0.0004672933,0.0001508072],"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":[0.0005387089,0.0002918291,0.002293822,0.0004000498,0.0007520122,0.0002990444,0.0007324516,0.4750363,0.006669239,0.2338047,0.00626728,0.2729146],"study_design_scores_gemma":[0.00001531809,0.00001850047,0.0002169995,0.0000127618,0.00003649518,0.00002674632,0.0000179894,0.8866677,0.0005610676,0.1116719,0.0007309628,0.00002361144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007132058,0.0003817388,0.9909115,0.000277165,0.00004219441,0.00002135997,0.0001035665,0.0003203732,0.0008099535],"genre_scores_gemma":[0.5655903,0.002022225,0.4216978,0.0004451984,0.0007984492,0.0004606751,0.001712149,0.0007180562,0.006555176],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004464366,"threshold_uncertainty_score":0.02361012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01568724593190495,"score_gpt":0.2629992289349489,"score_spread":0.2473119830030439,"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."}}