{"id":"W37346518","doi":"10.7717/peerj-cs.1363","title":"A Simple Closed-Class/Open-Class Factorization for Improved Language Modeling.","year":2001,"lang":"en","type":"article","venue":"NLPRS","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Zemkopības ministrija","keywords":"Perplexity; Language model; Class (philosophy); Computer science; Smoothing; Generalization; Function (biology); Simple (philosophy); Artificial intelligence; Natural language processing; Mathematics","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":[0.002990567,0.001232381,0.000809958,0.001532922,0.001402299,0.002692837,0.002351217,0.001674497,0.02499277],"category_scores_gemma":[0.009523786,0.0007657891,0.003145942,0.00113473,0.0008467557,0.004625705,0.002416585,0.002932444,0.01315085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078982,"about_ca_system_score_gemma":0.003156163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01210399,"about_ca_topic_score_gemma":0.01210599,"domain_scores_codex":[0.9972988,0.0006348408,0.0002486841,0.0008127977,0.0006991182,0.0003056965],"domain_scores_gemma":[0.9970432,0.00120269,0.000171963,0.0006042671,0.0008377488,0.0001401796],"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":[0.0005385297,0.0004456624,0.002760569,0.00039317,0.0001336346,0.000433233,0.0006457425,0.06156517,0.01263201,0.1175097,0.03131507,0.7716276],"study_design_scores_gemma":[0.00005026591,0.0000917454,0.0005668219,0.00006925564,0.00004352451,0.0002654941,0.0002549492,0.8593537,0.004988818,0.08811453,0.04614744,0.0000534578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002825585,0.0001112798,0.9896128,0.000208973,0.0001587875,0.000223159,0.0007503459,0.003211345,0.002897833],"genre_scores_gemma":[0.09122168,0.0001713712,0.8902231,0.0002436185,0.0001610731,0.000666845,0.004409222,0.001064779,0.01183824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02499277,"threshold_uncertainty_score":0.0836091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0361677065083973,"score_gpt":0.2954346646159682,"score_spread":0.2592669581075709,"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."}}