{"id":"W2055849934","doi":"10.1111/j.1467-8640.2010.00357.x","title":"AN EFFICIENT MODEL FOR ENHANCING TEXT CATEGORIZATION USING SENTENCE SEMANTICS","year":2010,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Natural language processing; Categorization; Computer science; Sentence; Phrase; Artificial intelligence; Term (time); Meaning (existential); Semantics (computer science); Set (abstract data type); Word (group theory); Linguistics; Psychology","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":[0.0002522901,0.0001358497,0.0001084917,0.0001626495,0.0002697419,0.0002454647,0.0008670637,0.00008316991,0.000006843834],"category_scores_gemma":[0.000129087,0.0001370383,0.00004597558,0.000374958,0.00009867283,0.000473232,0.0001070843,0.0001445873,0.00001941667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003309573,"about_ca_system_score_gemma":0.0001587729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005966288,"about_ca_topic_score_gemma":0.00001379678,"domain_scores_codex":[0.998735,0.00001453247,0.0003216268,0.0004323921,0.0002715967,0.0002248875],"domain_scores_gemma":[0.9987645,0.0001717571,0.000156662,0.0004037839,0.0004336771,0.00006960686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001299596,0.00004134909,0.00003770252,0.000005926459,0.000001983268,2.264763e-7,0.00024707,0.6120922,0.008512221,0.372273,0.000009931422,0.00677711],"study_design_scores_gemma":[0.00003586597,0.00002380723,0.00007107913,0.000007054099,0.000003374284,0.000006775845,0.00009637201,0.8731547,0.02112244,0.1053085,0.00002052313,0.0001495134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03545609,0.00001371015,0.9630983,0.0003997252,0.0004058394,0.000245335,0.000004124046,0.0003456725,0.00003116801],"genre_scores_gemma":[0.6031734,0.00000134469,0.3966781,0.0000677257,0.00002546792,0.00001389658,0.0000109331,0.000006174734,0.00002292729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5677174,"threshold_uncertainty_score":0.5588259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05018632138260581,"score_gpt":0.3334549231747679,"score_spread":0.2832686017921621,"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."}}