{"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/deepchannel-salience-estimation-by","title":"DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization","arxiv_id":"1811.02394","date":"2018-11-06","proceeding":null,"authors":["Jiaxin Shi","Chen Liang","Lei Hou","Juanzi Li","Zhiyuan Liu","Hanwang Zhang"],"abstract":"We propose DeepChannel, a robust, data-efficient, and interpretable neural\nmodel for extractive document summarization. Given any document-summary pair,\nwe estimate a salience score, which is modeled using an attention-based deep\nneural network, to represent the salience degree of the summary for yielding\nthe document. We devise a contrastive training strategy to learn the salience\nestimation network, and then use the learned salience score as a guide and\niteratively extract the most salient sentences from the document as our\ngenerated summary. In experiments, our model not only achieves state-of-the-art\nROUGE scores on CNN/Daily Mail dataset, but also shows strong robustness in the\nout-of-domain test on DUC2007 test set. Moreover, our model reaches a ROUGE-1\nF-1 score of 39.41 on CNN/Daily Mail test set with merely $1 / 100$ training\nset, demonstrating a tremendous data efficiency.","url_abs":"http://arxiv.org/abs/1811.02394v2","url_pdf":"http://arxiv.org/pdf/1811.02394v2.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":[{"paper_slug":"deepchannel-salience-estimation-by","repo_url":"https://github.com/lliangchenc/DeepChannel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"extractive-document-summarization-1","task_name":"Extractive Document Summarization"},{"task_slug":"extractive-document-summarization","task_name":"Extractive Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.02394","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}