{"id":"W21176108","doi":"10.1111/j.1742-7843.2010.00655.x","title":"Topic Segmentation : A First Stage to Dialog-Based Information Extraction.","year":2001,"lang":"en","type":"article","venue":"NLPRS","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Segmentation; Computer science; Dialog box; Information extraction; Artificial intelligence; Natural language processing; Hidden Markov model; Speech recognition; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001342639,0.00006818425,0.00006517817,0.0001252136,0.00009503608,0.0001592043,0.0002081798,0.00003764338,0.00004749193],"category_scores_gemma":[0.00004780735,0.00006594975,0.00002920237,0.0003100448,0.000005663912,0.0009579367,0.00002525087,0.0000421647,0.0006059164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007993913,"about_ca_system_score_gemma":0.00005119465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002786723,"about_ca_topic_score_gemma":0.0002028893,"domain_scores_codex":[0.999366,0.00002168935,0.0001686728,0.0001160564,0.0001730361,0.0001545383],"domain_scores_gemma":[0.9995131,0.00004132325,0.00006035895,0.0002451214,0.00005157715,0.00008848574],"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":[0.0001780777,0.000308931,0.05855392,0.0001807123,0.00004167074,0.0000834123,0.009978795,0.02494933,0.004743864,0.0332701,0.04504798,0.8226632],"study_design_scores_gemma":[0.002497779,0.0004934343,0.09473743,0.00005511299,0.000009473125,0.00003068786,0.0003447152,0.06232436,0.01296625,0.00113621,0.8247082,0.0006963631],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06396384,0.00001187654,0.9249165,0.001730771,0.0009396325,0.0002965266,0.000003849647,0.0001759837,0.007961003],"genre_scores_gemma":[0.9838353,0.000002771791,0.01378002,0.00163407,0.0001108571,0.00005809334,0.00002181913,0.000003237478,0.0005538319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9198714,"threshold_uncertainty_score":0.7788031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01560239395001572,"score_gpt":0.2559230316549126,"score_spread":0.2403206377048969,"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."}}