{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005962397,0.00004902881,0.00005128025,0.00002540093,0.00003153017,0.00007984718,0.0001636768,0.00001591203,0.00001647134],"category_scores_gemma":[0.000006482291,0.00003745348,0.0000133599,0.00005260627,0.000009855062,0.0001887034,0.00003081145,0.00004008957,0.00001102358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008494985,"about_ca_system_score_gemma":0.0000163995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007390911,"about_ca_topic_score_gemma":0.000001513409,"domain_scores_codex":[0.9995475,0.00001145983,0.00006649986,0.0001749046,0.00008745431,0.00011215],"domain_scores_gemma":[0.9996715,0.00001909295,0.00001230637,0.0002350118,0.0000082097,0.00005391471],"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":[0.000008911485,0.0003029313,0.003762082,0.0000196966,0.00001436997,0.00007425748,0.0008439826,0.0007137035,0.003052155,0.3881327,0.002245245,0.60083],"study_design_scores_gemma":[0.0004115659,0.0001099315,0.005875631,0.00001981455,0.000004259128,0.00001340347,0.00002724482,0.9836751,0.00199668,0.007159493,0.0005423248,0.0001645818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03394067,0.00002125248,0.9512189,0.01029648,0.00004686704,0.00004125559,9.570188e-8,0.00008606124,0.004348428],"genre_scores_gemma":[0.9174899,7.646473e-7,0.07870962,0.003482978,0.00001817128,0.000001047471,1.177754e-7,0.000001156179,0.0002962071],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9829614,"threshold_uncertainty_score":0.1527308,"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."}}