{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001824413,0.00007297166,0.000078447,0.00005208066,0.0001975446,0.0006333824,0.0004153173,0.00003083959,0.00006343691],"category_scores_gemma":[0.00003290696,0.00006751412,0.00004783584,0.0003087829,0.00002069017,0.0006490998,0.0001932212,0.00003395707,0.00002203332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002966203,"about_ca_system_score_gemma":0.0001369516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008899307,"about_ca_topic_score_gemma":0.00004834272,"domain_scores_codex":[0.998954,0.00002294586,0.0001500593,0.0004407076,0.0002233824,0.0002089166],"domain_scores_gemma":[0.9991561,0.00003399317,0.00002713389,0.0005412436,0.000181538,0.0000600321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008403911,0.0003477209,0.02785099,0.0001920574,0.00007183817,0.00005309887,0.002470687,0.006421571,0.009124652,0.6234249,0.009837463,0.3201966],"study_design_scores_gemma":[0.0005809342,0.0000142715,0.0009340505,0.0000296379,0.000007954007,0.00000489144,0.0001256497,0.9696562,0.01640329,0.00806481,0.003964093,0.0002142209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02309899,0.00004425883,0.973225,0.001467105,0.0009560451,0.0001485355,0.000002036857,0.00010801,0.000950046],"genre_scores_gemma":[0.8772685,0.00000263111,0.105058,0.0002766543,0.00007403515,0.0000250201,0.00005513434,0.000008649084,0.01723135],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9632346,"threshold_uncertainty_score":0.6107721,"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."}}