{"id":"W34986029","doi":"10.1089/cmb.2021.0438","title":"Exploiting Conversation Structure in Unsupervised Topic Segmentation for Emails","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Artificial intelligence; Natural language processing; Conversation; Segmentation; Exploit; Market segmentation; Thread (computing); Text segmentation; Information retrieval; Linguistics","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":[0.00267462,0.0001363694,0.0002303382,0.0004719557,0.0000935359,0.0003031885,0.0003377939,0.0001201748,0.0001946898],"category_scores_gemma":[0.003359394,0.0001034356,0.00006197851,0.0009179043,0.00003843133,0.001188457,0.00006209467,0.0004227288,0.000004355593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005938674,"about_ca_system_score_gemma":0.00004177211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000018322,"about_ca_topic_score_gemma":0.0001885326,"domain_scores_codex":[0.9980823,0.000219152,0.0006463227,0.0003210239,0.0004800114,0.0002512028],"domain_scores_gemma":[0.9984812,0.0009567597,0.000210484,0.0001622052,0.0001409364,0.00004843858],"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":[0.0000345721,0.00001660012,0.03415641,0.00003473535,0.000001615821,0.000003212827,0.01510369,0.00002410936,0.05885969,0.00006713976,0.00005587734,0.8916423],"study_design_scores_gemma":[0.005711562,0.0000951246,0.3952571,0.0001901106,0.00004566216,0.00001544265,0.09290363,0.395819,0.08027226,0.02516065,0.00333476,0.001194628],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9556915,0.0002855244,0.04198299,0.000927624,0.0004877356,0.000400962,0.000005300035,0.00003840705,0.0001799337],"genre_scores_gemma":[0.6626474,5.192638e-7,0.3365772,0.0005134796,0.00007866661,0.0000246687,0.00001789125,0.000006018422,0.0001341133],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8904477,"threshold_uncertainty_score":0.4217983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2587489947827946,"score_gpt":0.5735565170127669,"score_spread":0.3148075222299723,"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."}}