{"id":"W1547865988","doi":"10.1007/978-3-540-88192-6_10","title":"Enhancing Text Categorization Using Sentence Semantics","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Categorization; Natural language processing; Sentence; Phrase; Term (time); Weighting; Artificial intelligence; Set (abstract data type); Semantics (computer science); Meaning (existential); Text categorization; Word (group theory); Information retrieval; 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":[0.0007201555,0.0009890627,0.0008244044,0.002151814,0.0004754127,0.001264213,0.0006798792,0.0006772042,0.005202597],"category_scores_gemma":[0.002318466,0.0002042164,0.0008200203,0.001744595,0.0002385606,0.00297771,0.001076247,0.0008022938,0.004366781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002726319,"about_ca_system_score_gemma":0.0004768324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007352123,"about_ca_topic_score_gemma":0.001248792,"domain_scores_codex":[0.9994889,0.0001227606,0.00005667959,0.0001280928,0.000160601,0.00004290573],"domain_scores_gemma":[0.9985968,0.0005346497,0.00009090124,0.0001389335,0.0005810966,0.0000575261],"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":[0.0003859117,0.0003390405,0.001181526,0.0004826321,0.00006929864,0.0001267148,0.0002401123,0.002388202,0.1417512,0.003344978,0.02082206,0.8288682],"study_design_scores_gemma":[0.0002092523,0.001268007,0.008392013,0.000240307,0.000806818,0.001470042,0.001195638,0.5572176,0.2924755,0.06012718,0.07645696,0.0001406118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1237766,0.003099145,0.8437049,0.0008646567,0.001167107,0.0003251809,0.001897278,0.01392455,0.01124049],"genre_scores_gemma":[0.3817379,0.001327402,0.594223,0.0004970295,0.000785614,0.0002798009,0.007448212,0.001057247,0.01264376],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005202597,"threshold_uncertainty_score":0.01740438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02695655214121795,"score_gpt":0.2548127334415361,"score_spread":0.2278561813003182,"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."}}