{"id":"W4385572479","doi":"10.18653/v1/2023.codi-1.9","title":"Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Huawei Technologies","keywords":"Automatic summarization; Computer science; Consistency (knowledge bases); Relevance (law); Information retrieval; Multi-document summarization; Natural language processing; Component (thermodynamics); Artificial intelligence","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":[0.002343243,0.001233699,0.001019057,0.003270105,0.000827255,0.001609694,0.001438978,0.0009922076,0.004926165],"category_scores_gemma":[0.01061175,0.0002807838,0.0006197471,0.002419007,0.0005208009,0.003770716,0.002503855,0.001057778,0.001886259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000438381,"about_ca_system_score_gemma":0.000792918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001013973,"about_ca_topic_score_gemma":0.001216548,"domain_scores_codex":[0.9983488,0.0004302159,0.0002315327,0.0004522999,0.0004506272,0.00008656821],"domain_scores_gemma":[0.9945253,0.00177603,0.0006752311,0.001547324,0.001312433,0.0001637782],"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":[0.0005096866,0.0001852434,0.00256851,0.000922065,0.0001966368,0.0003822609,0.001556358,0.01081749,0.0985079,0.01177957,0.01415409,0.8584201],"study_design_scores_gemma":[0.0001969174,0.001079494,0.009875659,0.0002682747,0.0008807839,0.001189091,0.001363044,0.5500219,0.2810624,0.0402612,0.1135944,0.0002067366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0401883,0.001963251,0.943494,0.000381356,0.0002095184,0.0003486871,0.001311287,0.009475042,0.002628516],"genre_scores_gemma":[0.3144627,0.0008548917,0.6738053,0.0002185837,0.0003597206,0.000348933,0.005111109,0.0006986818,0.004140098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004926165,"threshold_uncertainty_score":0.01647967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03114916935483263,"score_gpt":0.2804351039777526,"score_spread":0.24928593462292,"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."}}