{"id":"W1520586504","doi":"10.1007/11424918_39","title":"Vocabulary Completion Through Word Cooccurrence Analysis Using Unlabeled Documents for Text Categorization","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Vocabulary; Text categorization; Categorization; Classifier (UML); Natural language processing; Artificial intelligence; Word (group theory); Vocabulary learning; Set (abstract data type); Training set; Information retrieval; Machine learning; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006054264,0.0005563241,0.000694817,0.001440697,0.0004717546,0.000818237,0.003164528,0.0003891087,0.00003282223],"category_scores_gemma":[0.0001019951,0.000538685,0.0002305709,0.002410444,0.0005994625,0.00158156,0.0008494482,0.0004571301,0.0000235319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006066436,"about_ca_system_score_gemma":0.0003764007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003034541,"about_ca_topic_score_gemma":0.00005736648,"domain_scores_codex":[0.9958606,0.00003486773,0.0007589778,0.001737007,0.0009494122,0.000659105],"domain_scores_gemma":[0.9969285,0.0003453158,0.000666959,0.001523471,0.0004450039,0.00009079496],"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":[0.00001437941,0.00008063058,0.0005454913,0.00005341673,0.0001239711,0.000007814587,0.0007401006,0.1068722,0.0005435824,0.1211118,0.00006302848,0.7698435],"study_design_scores_gemma":[0.0003897478,0.00009590799,0.0003086821,0.0001138264,0.0001098885,0.000008480381,5.577513e-7,0.8556623,0.001646545,0.1373871,0.003541386,0.0007355367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002504235,0.0004760619,0.9961346,0.0006975381,0.0009009319,0.0007583307,0.0000144858,0.0004014607,0.0003661516],"genre_scores_gemma":[0.3144579,0.0001149467,0.6840863,0.0006115709,0.0002498031,0.00003769882,0.00008543285,0.00002994144,0.0003264346],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.769108,"threshold_uncertainty_score":0.9997064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03748189831121202,"score_gpt":0.2981195490334377,"score_spread":0.2606376507222257,"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."}}