{"id":"W3154800935","doi":"10.18653/v1/2021.eacl-main.93","title":"Discourse-Aware Unsupervised Summarization for Long Scientific Documents","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Automatic summarization; Computer science; Exploit; Sentence; Graph; Artificial intelligence; Ranking (information retrieval); Natural language processing; Information retrieval; Topic model; Representation (politics); Machine learning; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001124736,0.001321251,0.0009598964,0.003837345,0.0005991011,0.001299015,0.001329589,0.0008652268,0.001578048],"category_scores_gemma":[0.004461779,0.0003790626,0.0008449898,0.00243672,0.0003431369,0.002031025,0.0008230362,0.001181371,0.001736568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007217887,"about_ca_system_score_gemma":0.001322244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003036448,"about_ca_topic_score_gemma":0.00860074,"domain_scores_codex":[0.9990181,0.0003352457,0.00007987076,0.0002743209,0.0002174867,0.00007491645],"domain_scores_gemma":[0.997255,0.001161515,0.0004902373,0.0002551548,0.000754151,0.00008386259],"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":[0.0003858433,0.0003876509,0.002795549,0.001044379,0.0003037917,0.0002883636,0.0008679551,0.09126769,0.05865626,0.010714,0.02199604,0.8112924],"study_design_scores_gemma":[0.0000510909,0.0002234792,0.00229869,0.00005824757,0.0001617484,0.0001040149,0.0002038791,0.9404069,0.025267,0.01905748,0.01211573,0.00005167728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03047005,0.00143441,0.9582313,0.0004453429,0.0001047888,0.0001871808,0.001389532,0.006003788,0.001733707],"genre_scores_gemma":[0.3546152,0.001230118,0.6200194,0.00024155,0.0006243536,0.0006222338,0.01365118,0.0009034607,0.008092533],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003837345,"threshold_uncertainty_score":0.006037533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02788662608596688,"score_gpt":0.2931997714278539,"score_spread":0.265313145341887,"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."}}