{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003764362,0.0004492957,0.0004063022,0.0009952112,0.0004146527,0.0004923663,0.002958796,0.0003524115,0.00001051844],"category_scores_gemma":[0.0001210668,0.0004290273,0.00009371008,0.0009419464,0.0007374173,0.0009901457,0.001227603,0.0006045428,0.00005031244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003954412,"about_ca_system_score_gemma":0.0005718154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002289494,"about_ca_topic_score_gemma":0.00003120309,"domain_scores_codex":[0.9966086,0.0000197275,0.0005599238,0.001327741,0.0009119512,0.0005720271],"domain_scores_gemma":[0.9975733,0.0002066696,0.000417,0.001418108,0.0002873977,0.00009756046],"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":[0.000004376934,0.00006421811,0.0003155673,0.00009358598,0.00002076461,0.000182366,0.002110519,0.04090714,0.009097582,0.1054203,0.00006735024,0.8417162],"study_design_scores_gemma":[0.0002093408,0.00009598215,0.0001211815,0.000376362,0.000009585126,0.0002072337,0.000001006759,0.870905,0.0363659,0.08877248,0.001952859,0.0009830967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002223252,0.0004021726,0.9957826,0.0007785641,0.001303906,0.0002815476,0.000001399881,0.0004828532,0.0007445951],"genre_scores_gemma":[0.3927287,0.000342767,0.6056191,0.0005458649,0.0002520776,0.000005538827,0.000005316652,0.00003596584,0.0004645948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8407332,"threshold_uncertainty_score":0.9998162,"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."}}