{"id":"W2161427841","doi":"","title":"Summarizing Emails with Conversational Cohesion and Subjectivity","year":2008,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Cohesion (chemistry); Computer science; PageRank; Cosine similarity; Natural language processing; Artificial intelligence; Graph; Sentence; Empirical research; Information retrieval; Subjectivity; Theoretical computer science; Pattern recognition (psychology); Mathematics","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":[0.0005475976,0.00008702647,0.0001557552,0.00006476924,0.0003661705,0.00002804876,0.0002327875,0.00004476954,2.688988e-7],"category_scores_gemma":[0.00470842,0.00007067721,0.00006115325,0.0002436779,0.00005630504,0.00006903361,0.0001041411,0.00007745086,4.074625e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441364,"about_ca_system_score_gemma":0.0001117305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001600998,"about_ca_topic_score_gemma":0.000007850972,"domain_scores_codex":[0.998931,0.00006599862,0.0002368311,0.000188357,0.0004577815,0.0001200251],"domain_scores_gemma":[0.9962969,0.001856415,0.0005642357,0.000132519,0.001124882,0.00002501478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003608725,0.0001057225,0.6116477,0.00005273688,0.0001581404,0.000001944237,0.0006961052,0.07089256,0.0002573885,0.3148366,0.00085511,0.0004598935],"study_design_scores_gemma":[0.001315175,0.0002075095,0.2991844,0.0001450173,0.0001055637,0.00001835701,0.00003321941,0.5126092,0.006137724,0.1761356,0.003662907,0.0004452879],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07226845,0.00003212084,0.9253579,0.0004662924,0.0002111419,0.0002940832,0.00001888923,0.0001294875,0.001221631],"genre_scores_gemma":[0.7667304,0.000002116247,0.2330418,0.00005520412,0.00006129601,0.000005775817,0.000008838416,0.000005578057,0.00008905098],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6944619,"threshold_uncertainty_score":0.5636758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01336756495223629,"score_gpt":0.2436825173727591,"score_spread":0.2303149524205229,"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."}}