{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001486835,0.001348887,0.001872065,0.005170802,0.001215396,0.001590724,0.001790025,0.001154051,0.003885938],"category_scores_gemma":[0.004503657,0.0004571089,0.001440494,0.004445773,0.0006333578,0.002343039,0.001575548,0.001756525,0.004740624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004449764,"about_ca_system_score_gemma":0.001866493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005096616,"about_ca_topic_score_gemma":0.007250659,"domain_scores_codex":[0.9982709,0.0003538179,0.0002023744,0.0005329081,0.0004714942,0.0001684621],"domain_scores_gemma":[0.9969468,0.00129564,0.000163771,0.0004536336,0.001029789,0.0001104429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003813374,0.0003692536,0.001116098,0.0003486125,0.00009700979,0.0001054111,0.0002701726,0.003686324,0.06941164,0.002216925,0.008691513,0.9133057],"study_design_scores_gemma":[0.0001769217,0.0004969896,0.005156596,0.0001548995,0.0004391219,0.0006872665,0.001049942,0.8110551,0.1183336,0.03851304,0.0237819,0.0001547345],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04021281,0.001472985,0.9487871,0.0001610346,0.000280403,0.0004288764,0.001150418,0.00552063,0.001985749],"genre_scores_gemma":[0.1770448,0.000912248,0.8047009,0.00009954569,0.0002757829,0.0006469415,0.00835673,0.0006502203,0.007312811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005170802,"threshold_uncertainty_score":0.01299971,"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."}}