{"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/incorporating-word-attention-into-character","title":"Incorporating Word Attention into Character-Based Word Segmentation","arxiv_id":null,"date":"2019-06-01","proceeding":"NAACL 2019 6","authors":["Shohei Higashiyama","Masao Utiyama","Eiichiro Sumita","Masao Ideuchi","Yoshiaki Oida","Yohei Sakamoto","Isaac Okada"],"abstract":"Neural network models have been actively applied to word segmentation, especially Chinese, because of the ability to minimize the effort in feature engineering. Typical segmentation models are categorized as character-based, for conducting exact inference, or word-based, for utilizing word-level information. We propose a character-based model utilizing word information to leverage the advantages of both types of models. Our model learns the importance of multiple candidate words for a character on the basis of an attention mechanism, and makes use of it for segmentation decisions. The experimental results show that our model achieves better performance than the state-of-the-art models on both Japanese and Chinese benchmark datasets.","url_abs":"https://aclanthology.org/N19-1276","url_pdf":"https://aclanthology.org/N19-1276.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":"incorporating-word-attention-into-character","repo_url":"https://github.com/shigashiyama/seikanlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"japanese-word-segmentation","task_name":"Japanese Word Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/japanese-word-segmentation-on-bccwj","task":"Japanese Word Segmentation","dataset":"BCCWJ","model":"Word Attention","rank_in_archive_order":2,"of":3,"metrics":{"F1-score (Word)":"0.9893"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}