{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-latent-extractive-document","title":"Neural Latent Extractive Document Summarization","arxiv_id":"1808.07187","date":"2018-08-22","proceeding":"EMNLP 2018 10","authors":["Xingxing Zhang","Mirella Lapata","Furu Wei","Ming Zhou"],"abstract":"Extractive summarization models require sentence-level labels, which are\nusually created heuristically (e.g., with rule-based methods) given that most\nsummarization datasets only have document-summary pairs. Since these labels\nmight be suboptimal, we propose a latent variable extractive model where\nsentences are viewed as latent variables and sentences with activated variables\nare used to infer gold summaries. During training the loss comes\n\\emph{directly} from gold summaries. Experiments on the CNN/Dailymail dataset\nshow that our model improves over a strong extractive baseline trained on\nheuristically approximated labels and also performs competitively to several\nrecent models.","url_abs":"http://arxiv.org/abs/1808.07187v2","url_pdf":"http://arxiv.org/pdf/1808.07187v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"extractive-document-summarization-1","task_name":"Extractive Document Summarization"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"extractive-document-summarization","task_name":"Extractive Text Summarization"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/extractive-document-summarization-on-cnn","task":"Extractive Text Summarization","dataset":"CNN / Daily Mail","model":"Latent","rank_in_archive_order":12,"of":15,"metrics":{"ROUGE-1":"41.05","ROUGE-2":"18.77","ROUGE-L":"37.54"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.07187","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}