{"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/neural-word-segmentation-with-rich","title":"Neural Word Segmentation with Rich Pretraining","arxiv_id":"1704.08960","date":"2017-04-28","proceeding":"ACL 2017 7","authors":["Jie Yang","Yue Zhang","Fei Dong"],"abstract":"Neural word segmentation research has benefited from large-scale raw texts by\nleveraging them for pretraining character and word embeddings. On the other\nhand, statistical segmentation research has exploited richer sources of\nexternal information, such as punctuation, automatic segmentation and POS. We\ninvestigate the effectiveness of a range of external training sources for\nneural word segmentation by building a modular segmentation model, pretraining\nthe most important submodule using rich external sources. Results show that\nsuch pretraining significantly improves the model, leading to accuracies\ncompetitive to the best methods on six benchmarks.","url_abs":"http://arxiv.org/abs/1704.08960v1","url_pdf":"http://arxiv.org/pdf/1704.08960v1.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":"neural-word-segmentation-with-rich","repo_url":"https://github.com/jiesutd/RichWordSegmentor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"pos","task_name":"POS"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.08960","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}