{"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/leveraging-discourse-information-effectively","title":"Leveraging Discourse Information Effectively for Authorship Attribution","arxiv_id":"1709.02271","date":"2017-09-07","proceeding":"IJCNLP 2017 11","authors":["Su Wang","Elisa Ferracane","Raymond J. Mooney"],"abstract":"We explore techniques to maximize the effectiveness of discourse information\nin the task of authorship attribution. We present a novel method to embed\ndiscourse features in a Convolutional Neural Network text classifier, which\nachieves a state-of-the-art result by a substantial margin. We empirically\ninvestigate several featurization methods to understand the conditions under\nwhich discourse features contribute non-trivial performance gains, and analyze\ndiscourse embeddings.","url_abs":"http://arxiv.org/abs/1709.02271v1","url_pdf":"http://arxiv.org/pdf/1709.02271v1.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":"leveraging-discourse-information-effectively","repo_url":"https://github.com/elisaF/authorship-attribution-discourse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"authorship-attribution","task_name":"Authorship Attribution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.02271","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}