{"id":"W2400208831","doi":"","title":"Bag of Senses Versus Bag of Words: Comparing Semantic and Lexical Approaches on Sentence Extraction.","year":2008,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Sentence; Bag-of-words model","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002372594,0.00007300427,0.0001706494,0.00005876507,0.00009746708,0.000008564803,0.0001763467,0.00003054281,0.00000151238],"category_scores_gemma":[0.00002829594,0.00006611238,0.00002213339,0.0001351991,0.0003962869,0.0001358749,0.00008126288,0.00006333172,5.655698e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004188266,"about_ca_system_score_gemma":0.00002176995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001769321,"about_ca_topic_score_gemma":0.000001830049,"domain_scores_codex":[0.9993714,0.00004664846,0.0002086549,0.0001850187,0.000110632,0.00007763031],"domain_scores_gemma":[0.9990839,0.0003983728,0.0001198216,0.0003227988,0.00004505013,0.00003010273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006784381,0.00006605627,0.0006054544,0.0000699282,0.00001425172,2.963182e-7,0.001369468,0.0005250919,0.001331725,0.9823411,0.000002170368,0.01360662],"study_design_scores_gemma":[0.002334297,0.0005155233,0.01673739,0.0002056417,0.0001335208,0.0001624373,0.009572666,0.1103506,0.2759949,0.5826822,0.0005675908,0.0007432337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5292881,0.0002805798,0.4693988,0.00005803398,0.00001972037,0.00009260292,0.000001237652,0.00001781904,0.0008431309],"genre_scores_gemma":[0.9902785,0.00009493867,0.00953815,0.000004940193,0.00002036712,0.00001621535,0.000001093381,0.000002951896,0.00004278322],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4609905,"threshold_uncertainty_score":0.2695985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06651501571551183,"score_gpt":0.272761717985147,"score_spread":0.2062467022696352,"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."}}