{"id":"W2106854223","doi":"10.1111/j.1467-8640.2012.00436.x","title":"EXPLOITING SYNTACTIC, SEMANTIC, AND LEXICAL REGULARITIES IN LANGUAGE MODELING VIA DIRECTED MARKOV RANDOM FIELDS","year":2012,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Language model; Perplexity; Computer science; Trigram; Probabilistic latent semantic analysis; Artificial intelligence; Natural language processing; Smoothing; Context (archaeology); Algorithm","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":[0.0004553875,0.000139191,0.0001767193,0.0001583472,0.00009665332,0.0001376376,0.0003538554,0.00008383967,0.000011634],"category_scores_gemma":[0.0002427063,0.0001334331,0.0000333813,0.0002761674,0.00005038517,0.0008467692,0.0002376002,0.0002447695,0.000005771044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004024643,"about_ca_system_score_gemma":0.00002741203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001153453,"about_ca_topic_score_gemma":0.00001175313,"domain_scores_codex":[0.9988129,0.00009282542,0.0002914668,0.0002644613,0.0002478856,0.0002905284],"domain_scores_gemma":[0.9991032,0.0005011566,0.00006447081,0.0001605545,0.00008975477,0.00008089578],"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":[0.0001522895,0.0003905135,0.004640082,0.0004349381,0.00006721892,0.00017166,0.03051685,0.0452129,0.002351573,0.244103,0.0001542044,0.6718047],"study_design_scores_gemma":[0.00008201195,0.000012167,0.0001272191,0.0001061537,0.000003197486,0.00007395484,0.0001890705,0.9209285,0.004035176,0.07427141,0.00000281465,0.0001683721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03710725,0.004556639,0.9573082,0.0003292116,0.0001144688,0.0001127786,7.618976e-7,0.000341843,0.0001287947],"genre_scores_gemma":[0.6305614,0.00001535379,0.3691904,0.0001499058,0.00004685478,0.0000100138,0.000003522088,0.000005928126,0.00001667386],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8757156,"threshold_uncertainty_score":0.5441245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02393159905830056,"score_gpt":0.2965222874839078,"score_spread":0.2725906884256072,"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."}}