{"id":"W2696068122","doi":"10.18653/v1/w17-2407","title":"Extract with Order for Coherent Multi-Document Summarization","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; University of Lethbridge","keywords":"Automatic summarization; Readability; Computer science; Coherence (philosophical gambling strategy); Rank (graph theory); Natural language processing; Key (lock); Artificial intelligence; Information retrieval; Selection (genetic algorithm); Sentence; Multi-document summarization; Mathematics","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":[0.001433838,0.001435145,0.001095292,0.002749308,0.0005510398,0.001747768,0.0008088999,0.0008387951,0.003757919],"category_scores_gemma":[0.0055039,0.0004378431,0.0009019498,0.001721069,0.0003566716,0.00254328,0.001083608,0.001494873,0.003790335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004631646,"about_ca_system_score_gemma":0.000981883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009832521,"about_ca_topic_score_gemma":0.002777559,"domain_scores_codex":[0.9987739,0.0002978104,0.000147836,0.0003063139,0.0003823838,0.0000916584],"domain_scores_gemma":[0.9970414,0.00111198,0.0003559406,0.0005792108,0.0008016568,0.0001096829],"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":[0.0005317953,0.0002071846,0.001094942,0.000725102,0.0001872671,0.0002733788,0.0004666154,0.02127719,0.06115494,0.009721301,0.02368873,0.8806716],"study_design_scores_gemma":[0.0002078427,0.001460413,0.003911271,0.000166615,0.0006048201,0.0007232663,0.0006016661,0.7499978,0.1228084,0.05294148,0.06641773,0.0001587533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01546595,0.001878616,0.9733107,0.0003276261,0.0002388481,0.0001608427,0.001190425,0.006204026,0.001222987],"genre_scores_gemma":[0.1856345,0.001271875,0.7950914,0.0003115924,0.0006311071,0.0003149605,0.00783077,0.0008190071,0.008094859],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003757919,"threshold_uncertainty_score":0.01257151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02839285591499323,"score_gpt":0.3345133148343654,"score_spread":0.3061204589193722,"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."}}