{"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/two-pass-discourse-segmentation-with-pairing","title":"Two-pass Discourse Segmentation with Pairing and Global Features","arxiv_id":"1407.8215","date":"2014-07-30","proceeding":null,"authors":["Vanessa Wei Feng","Graeme Hirst"],"abstract":"Previous attempts at RST-style discourse segmentation typically adopt\nfeatures centered on a single token to predict whether to insert a boundary\nbefore that token. In contrast, we develop a discourse segmenter utilizing a\nset of pairing features, which are centered on a pair of adjacent tokens in the\nsentence, by equally taking into account the information from both tokens.\nMoreover, we propose a novel set of global features, which encode\ncharacteristics of the segmentation as a whole, once we have an initial\nsegmentation. We show that both the pairing and global features are useful on\ntheir own, and their combination achieved an $F_1$ of 92.6% of identifying\nin-sentence discourse boundaries, which is a 17.8% error-rate reduction over\nthe state-of-the-art performance, approaching 95% of human performance. In\naddition, similar improvement is observed across different classification\nframeworks.","url_abs":"http://arxiv.org/abs/1407.8215v1","url_pdf":"http://arxiv.org/pdf/1407.8215v1.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":"two-pass-discourse-segmentation-with-pairing","repo_url":"https://github.com/Akanni96/feng-hirst-rst-parser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"two-pass-discourse-segmentation-with-pairing","repo_url":"https://github.com/NLPbox/feng-hirst-service","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"two-pass-discourse-segmentation-with-pairing","repo_url":"https://github.com/ZiningZhu/feng-hirst-rst-parser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"two-pass-discourse-segmentation-with-pairing","repo_url":"https://github.com/arne-cl/feng-hirst-rst-parser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"discourse-segmentation","task_name":"Discourse Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}