{"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-discourse-structure-for-text","title":"Neural Discourse Structure for Text Categorization","arxiv_id":"1702.01829","date":"2017-02-07","proceeding":"ACL 2017 7","authors":["Yangfeng Ji","Noah Smith"],"abstract":"We show that discourse structure, as defined by Rhetorical Structure Theory\nand provided by an existing discourse parser, benefits text categorization. Our\napproach uses a recursive neural network and a newly proposed attention\nmechanism to compute a representation of the text that focuses on salient\ncontent, from the perspective of both RST and the task. Experiments consider\nvariants of the approach and illustrate its strengths and weaknesses.","url_abs":"http://arxiv.org/abs/1702.01829v2","url_pdf":"http://arxiv.org/pdf/1702.01829v2.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":"neural-discourse-structure-for-text","repo_url":"https://github.com/jiyfeng/disco4textcat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"text-categorization","task_name":"Text Categorization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1702.01829","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}