{"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/toward-fast-and-accurate-neural-discourse","title":"Toward Fast and Accurate Neural Discourse Segmentation","arxiv_id":"1808.09147","date":"2018-08-28","proceeding":"EMNLP 2018 10","authors":["Yizhong Wang","Sujian Li","Jingfeng Yang"],"abstract":"Discourse segmentation, which segments texts into Elementary Discourse Units,\nis a fundamental step in discourse analysis. Previous discourse segmenters rely\non complicated hand-crafted features and are not practical in actual use. In\nthis paper, we propose an end-to-end neural segmenter based on BiLSTM-CRF\nframework. To improve its accuracy, we address the problem of data\ninsufficiency by transferring a word representation model that is trained on a\nlarge corpus. We also propose a restricted self-attention mechanism in order to\ncapture useful information within a neighborhood. Experiments on the RST-DT\ncorpus show that our model is significantly faster than previous methods, while\nachieving new state-of-the-art performance.","url_abs":"http://arxiv.org/abs/1808.09147v1","url_pdf":"http://arxiv.org/pdf/1808.09147v1.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":"toward-fast-and-accurate-neural-discourse","repo_url":"https://github.com/PKU-TANGENT/NeuralEDUSeg","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"discourse-segmentation","task_name":"Discourse Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09147","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}