{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004868242,0.0001414666,0.000145502,0.00004748182,0.0002771956,0.0001625171,0.0006633482,0.00003990721,0.00007536501],"category_scores_gemma":[0.00006241328,0.0001031102,0.00004560754,0.000119502,0.00002720913,0.0002645339,0.000440792,0.0004790771,0.00009269647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005357061,"about_ca_system_score_gemma":0.00002265732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001570934,"about_ca_topic_score_gemma":0.00002728787,"domain_scores_codex":[0.9985775,0.0001663106,0.0002381417,0.0003310402,0.0003213581,0.0003656601],"domain_scores_gemma":[0.9992224,0.0001481433,0.0000801576,0.0004399618,0.00002496547,0.00008438594],"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":[0.000005801075,0.0000400776,0.002465698,0.000008754802,0.00001843728,0.00003218776,0.004614748,0.6607096,0.0006818054,0.1675471,0.00003881834,0.163837],"study_design_scores_gemma":[0.0002703135,0.00003166196,0.0003770668,0.000008222753,0.000005176218,0.00002390172,0.00002437863,0.9901963,0.0001117959,0.003860506,0.004961915,0.000128799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05609526,0.0002453371,0.9397546,0.002084111,0.0001125145,0.0001058637,0.000001170526,0.0002564914,0.001344641],"genre_scores_gemma":[0.8941785,0.000005206549,0.1046262,0.0004627486,0.0001182841,0.000008327413,0.000006617094,0.00001469042,0.0005793872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8380832,"threshold_uncertainty_score":0.4204711,"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."}}