{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007183796,0.0007949167,0.001184686,0.008631789,0.0007236032,0.002891467,0.001208668,0.001021886,0.002209491],"category_scores_gemma":[0.03668996,0.000321314,0.001095476,0.008057047,0.0006211335,0.007742796,0.001955882,0.0009964966,0.001570564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006142858,"about_ca_system_score_gemma":0.00156079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001771002,"about_ca_topic_score_gemma":0.004117208,"domain_scores_codex":[0.9929888,0.004194082,0.0005955154,0.0006580477,0.001363196,0.0002004563],"domain_scores_gemma":[0.9701173,0.02514009,0.0009520181,0.0009637014,0.002532302,0.0002945549],"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":[0.001672625,0.0003558017,0.01799842,0.002440138,0.0006234554,0.0001415751,0.001205065,0.003369105,0.009508065,0.01328695,0.02212345,0.9272753],"study_design_scores_gemma":[0.0008251234,0.002507152,0.0970965,0.00223575,0.00360824,0.002644903,0.010811,0.4938559,0.04143739,0.2418204,0.1025725,0.0005852109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2155926,0.02405951,0.7198666,0.003261418,0.001271839,0.00122151,0.01192523,0.004841794,0.01795942],"genre_scores_gemma":[0.5066038,0.00648223,0.46548,0.0005303111,0.0008658673,0.0008284018,0.01598677,0.0005996234,0.002623202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008631789,"threshold_uncertainty_score":0.03799194,"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."}}