{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003324555,0.001226314,0.0009969994,0.004025226,0.0008412492,0.002490154,0.0007553663,0.001119899,0.0009375978],"category_scores_gemma":[0.02397137,0.0005320183,0.0007730604,0.002409586,0.0006215124,0.005029156,0.001353118,0.0006785095,0.0005331694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005924078,"about_ca_system_score_gemma":0.0006183968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001079974,"about_ca_topic_score_gemma":0.001503333,"domain_scores_codex":[0.9968136,0.001583424,0.0003205725,0.0005923277,0.0005747551,0.0001153062],"domain_scores_gemma":[0.9846705,0.01024063,0.00188392,0.001042944,0.001932597,0.0002294712],"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":[0.0009966069,0.0002481605,0.01733918,0.002727068,0.0006065104,0.0008823901,0.006635359,0.06530467,0.04592604,0.02422825,0.007312474,0.8277934],"study_design_scores_gemma":[0.00009275175,0.0007253079,0.0205816,0.0003130655,0.00109194,0.0009415674,0.004252906,0.7659903,0.04293973,0.1387453,0.02412135,0.0002041328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1160832,0.002279369,0.8766132,0.0006805406,0.000121476,0.0002138822,0.0004842319,0.001350205,0.002173785],"genre_scores_gemma":[0.5672662,0.001268927,0.4265423,0.0001388247,0.0004897352,0.0002102353,0.001941613,0.0002504736,0.001891817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004025226,"threshold_uncertainty_score":0.01758212,"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."}}