{"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/effective-neural-solution-for-multi-criteria","title":"Effective Neural Solution for Multi-Criteria Word Segmentation","arxiv_id":"1712.02856","date":"2017-12-07","proceeding":null,"authors":["Han He","Lei Wu","Hua Yan","Zhimin Gao","Yi Feng","George Townsend"],"abstract":"We present a simple yet elegant solution to train a single joint model on\nmulti-criteria corpora for Chinese Word Segmentation (CWS). Our novel design\nrequires no private layers in model architecture, instead, introduces two\nartificial tokens at the beginning and ending of input sentence to specify the\nrequired target criteria. The rest of the model including Long Short-Term\nMemory (LSTM) layer and Conditional Random Fields (CRFs) layer remains\nunchanged and is shared across all datasets, keeping the size of parameter\ncollection minimal and constant. On Bakeoff 2005 and Bakeoff 2008 datasets, our\ninnovative design has surpassed both single-criterion and multi-criteria\nstate-of-the-art learning results. To the best knowledge, our design is the\nfirst one that has achieved the latest high performance on such large scale\ndatasets. Source codes and corpora of this paper are available on GitHub.","url_abs":"http://arxiv.org/abs/1712.02856v2","url_pdf":"http://arxiv.org/pdf/1712.02856v2.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":"effective-neural-solution-for-multi-criteria","repo_url":"https://github.com/hankcs/multi-criteria-cws","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"chinese-word-segmentation","task_name":"Chinese Word Segmentation"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}