{"id":"W1557217172","doi":"10.1007/978-3-540-74628-7_21","title":"Word Distribution Based Methods for Minimizing Segment Overlaps","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cohesion (chemistry); Computer science; Natural language processing; Text segmentation; Word (group theory); Segmentation; Artificial intelligence; Task (project management); Sequence (biology); Linguistics; Engineering","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":[0.002006322,0.002084437,0.002706222,0.004299731,0.001216564,0.001797777,0.002992321,0.002398735,0.008062995],"category_scores_gemma":[0.005684533,0.001127954,0.001627088,0.005348971,0.001017199,0.003083541,0.002391948,0.001807463,0.004427964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008658837,"about_ca_system_score_gemma":0.001789801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005202303,"about_ca_topic_score_gemma":0.01160726,"domain_scores_codex":[0.9979587,0.0003712217,0.0001776923,0.0005454242,0.0007522067,0.0001947607],"domain_scores_gemma":[0.9956859,0.002610653,0.0001720266,0.00043923,0.0009807068,0.0001115758],"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":[0.0006968411,0.0001892673,0.001208247,0.0003745491,0.0001585371,0.0001700052,0.0002195813,0.06102824,0.02311017,0.008560121,0.009452296,0.8948322],"study_design_scores_gemma":[0.0000897848,0.0001563211,0.001259918,0.00004496466,0.0001434067,0.0002712799,0.0001641575,0.9440269,0.02003903,0.02479161,0.00897041,0.00004228339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01077248,0.0008213095,0.9845659,0.00008299655,0.00008688646,0.0000922589,0.0002980771,0.002331243,0.0009487819],"genre_scores_gemma":[0.1030876,0.0008706648,0.8786234,0.0001918266,0.0002347065,0.0004504539,0.004070886,0.002118069,0.01035235],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008062995,"threshold_uncertainty_score":0.02697337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03036712204334569,"score_gpt":0.3420866313372177,"score_spread":0.311719509293872,"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."}}