{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002214629,0.000139262,0.0001664638,0.00006758183,0.0001327033,0.0002784618,0.001045959,0.00009072214,0.00001841077],"category_scores_gemma":[0.00009030217,0.0001345578,0.00006203548,0.0002100666,0.000008734827,0.0006223234,0.0002817706,0.00009915562,0.00001949984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007450448,"about_ca_system_score_gemma":0.00008926582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00026228,"about_ca_topic_score_gemma":0.0001154798,"domain_scores_codex":[0.9988127,0.00002708269,0.0002460147,0.0004492536,0.0001261987,0.0003387001],"domain_scores_gemma":[0.9990419,0.00005801767,0.0000793618,0.0006282974,0.0001018316,0.00009065407],"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":[0.0001206689,0.0003607324,0.0009454219,0.00009064093,0.000093029,0.00002911641,0.007011638,0.06533454,0.05961847,0.17047,0.004686174,0.6912395],"study_design_scores_gemma":[0.0005858401,0.00004780188,0.00002334735,0.000005503738,0.000004889327,0.000003312286,0.00006047971,0.9773334,0.0006889978,0.008114464,0.01296119,0.0001707244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04862573,0.00005707538,0.9475864,0.0009183332,0.0003437624,0.00048119,0.000008453005,0.0001975201,0.001781512],"genre_scores_gemma":[0.9548913,0.00000844799,0.04311212,0.0008066258,0.0001853589,0.00005728676,0.00002479736,0.00001953893,0.0008945438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9119989,"threshold_uncertainty_score":0.548711,"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."}}