{"id":"W3217119495","doi":"10.1109/access.2021.3129786","title":"A Survey of Automatic Text Summarization: Progress, Process and Challenges","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Topic Modeling","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Automatic summarization; Computer science; Workflow; Taxonomy (biology); Information retrieval; Domain (mathematical analysis); Text graph; Process (computing); The Internet; Feature extraction; Data science; Artificial intelligence; World Wide Web; Database","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":[0.0002647275,0.00007843514,0.000154429,0.00004290273,0.00004137257,0.0001651828,0.0005986165,0.0000420285,0.000007046182],"category_scores_gemma":[0.00008477694,0.00007375544,0.00001287192,0.0003435405,0.00003806147,0.000625845,0.0001912948,0.00005004616,0.000001558712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006718446,"about_ca_system_score_gemma":0.0001384773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000322298,"about_ca_topic_score_gemma":0.000140631,"domain_scores_codex":[0.9990823,0.00008880054,0.0001961907,0.0002955509,0.000207364,0.0001297593],"domain_scores_gemma":[0.9991382,0.0000871163,0.00009599152,0.0003551138,0.0002805542,0.00004303958],"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":[0.000003171591,0.0001871947,0.1213395,0.001602893,0.00005028141,0.0000413774,0.002385157,0.0004223085,0.0000810562,0.006284989,0.00009923038,0.8675029],"study_design_scores_gemma":[0.0004295059,0.00003376731,0.4277271,0.0002153518,0.00001036995,0.00002597201,0.00004510763,0.55734,0.009702701,0.0040665,0.0001163347,0.0002872162],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7137206,0.01787327,0.2628039,0.003285536,0.0006387184,0.0003094132,0.000005548581,0.0002459534,0.001117006],"genre_scores_gemma":[0.9961594,0.0003124174,0.003406693,0.00005121545,0.00002418292,0.00001474372,0.000001996694,0.000005712749,0.00002358553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8672156,"threshold_uncertainty_score":0.3007659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08943312503184098,"score_gpt":0.3288187108396128,"score_spread":0.2393855858077719,"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."}}