{"id":"W2144173701","doi":"10.3115/1667583.1667609","title":"A syntactic and lexical-based discourse segmenter","year":2009,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Parsing; Computer science; Artificial intelligence; Natural language processing; Probabilistic logic; Recall; Market segmentation; Segmentation; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002306575,0.001217672,0.001140189,0.002512909,0.000928177,0.001787383,0.001696927,0.001748863,0.01819033],"category_scores_gemma":[0.008151984,0.0009183791,0.0007528587,0.001343679,0.000820027,0.004796744,0.001830282,0.002066132,0.01104767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005066207,"about_ca_system_score_gemma":0.001136114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001339703,"about_ca_topic_score_gemma":0.001609031,"domain_scores_codex":[0.998514,0.0003020889,0.0001157521,0.0005510277,0.0004468849,0.00007037928],"domain_scores_gemma":[0.9944459,0.003169953,0.0003415211,0.0007690665,0.001103,0.0001705351],"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":[0.0006089143,0.0002492775,0.002651128,0.000768991,0.0001041801,0.0004425725,0.002150515,0.004845155,0.1645823,0.01742267,0.03748706,0.7686872],"study_design_scores_gemma":[0.0002329248,0.0005541556,0.005841732,0.0001582502,0.0003031415,0.002065436,0.001107811,0.3530687,0.3797266,0.02699008,0.2296057,0.0003454072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01556833,0.0002921794,0.9199413,0.0003726615,0.0001490186,0.0002511059,0.001787875,0.05743733,0.004200164],"genre_scores_gemma":[0.07150134,0.0002431426,0.9097292,0.0002609264,0.0001611226,0.0003194925,0.004055484,0.003507679,0.01022149],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01819033,"threshold_uncertainty_score":0.06085271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01812517314559017,"score_gpt":0.275855511870072,"score_spread":0.2577303387244819,"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."}}