{"id":"W1588617094","doi":"10.1007/978-3-642-15760-8_27","title":"Coverage-Based Methods for Distributional Stopword Selection in Text Segmentation","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Selection (genetic algorithm); Segmentation; Measure (data warehouse); Representation (politics); Word (group theory); Artificial intelligence; Natural language processing; Information retrieval; Data mining; Mathematics","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":[0.005014348,0.001990268,0.003953756,0.007750871,0.001892293,0.00295176,0.003334352,0.003146634,0.005511257],"category_scores_gemma":[0.01730248,0.001230038,0.001924393,0.007033762,0.001273371,0.004039393,0.003456311,0.002921167,0.004552717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000800426,"about_ca_system_score_gemma":0.001738071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005492121,"about_ca_topic_score_gemma":0.0114188,"domain_scores_codex":[0.9949956,0.001712877,0.0005421738,0.001038986,0.001323118,0.0003872503],"domain_scores_gemma":[0.9773155,0.01728167,0.0006744729,0.001471043,0.0028321,0.0004251769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00120227,0.0003023549,0.004019498,0.0007236052,0.0004654418,0.000325033,0.000632644,0.04096049,0.02570106,0.008029514,0.01466085,0.9029772],"study_design_scores_gemma":[0.00008636521,0.0001279442,0.002203568,0.00005758422,0.0001637213,0.0002819916,0.0002004202,0.9662454,0.009802453,0.01619393,0.004574085,0.00006257233],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02249568,0.001838778,0.9679394,0.000180322,0.0001354223,0.0001481335,0.0006926201,0.005327701,0.001241885],"genre_scores_gemma":[0.2824008,0.001198135,0.6954201,0.0003014177,0.000706482,0.0007331484,0.009569204,0.003839082,0.005831536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007750871,"threshold_uncertainty_score":0.0265187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02436505187435277,"score_gpt":0.3166291836962259,"score_spread":0.2922641318218732,"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."}}