{"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/state-of-the-art-chinese-word-segmentation","title":"State-of-the-art Chinese Word Segmentation with Bi-LSTMs","arxiv_id":"1808.06511","date":"2018-08-20","proceeding":"EMNLP 2018 10","authors":["Ji Ma","Kuzman Ganchev","David Weiss"],"abstract":"A wide variety of neural-network architectures have been proposed for the\ntask of Chinese word segmentation.\n  Surprisingly, we find that a bidirectional LSTM model, when combined with\nstandard deep learning techniques and best practices, can achieve better\naccuracy on many of the popular datasets as compared to models based on more\ncomplex neural-network architectures.\n  Furthermore, our error analysis shows that out-of-vocabulary words remain\nchallenging for neural-network models, and many of the remaining errors are\nunlikely to be fixed through architecture changes.\n  Instead, more effort should be made on exploring resources for further\nimprovement.","url_abs":"http://arxiv.org/abs/1808.06511v2","url_pdf":"http://arxiv.org/pdf/1808.06511v2.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":"state-of-the-art-chinese-word-segmentation","repo_url":"https://github.com/efeatikkan/Chinese_Word_Segmenter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"chinese-word-segmentation","task_name":"Chinese Word Segmentation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.06511","atlas_url":"https://app.syntology.ai/?focus=1808.06511","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}