{"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/chinese-pinyin-aided-ime-input-what-you-have","title":"Chinese Pinyin Aided IME, Input What You Have Not Keystroked Yet","arxiv_id":"1809.00329","date":"2018-09-02","proceeding":"EMNLP 2018 10","authors":["Yafang Huang","Hai Zhao"],"abstract":"Chinese pinyin input method engine (IME) converts pinyin into character so\nthat Chinese characters can be conveniently inputted into computer through\ncommon keyboard. IMEs work relying on its core component, pinyin-to-character\nconversion (P2C). Usually Chinese IMEs simply predict a list of character\nsequences for user choice only according to user pinyin input at each turn.\nHowever, Chinese inputting is a multi-turn online procedure, which can be\nsupposed to be exploited for further user experience promoting. This paper thus\nfor the first time introduces a sequence-to-sequence model with gated-attention\nmechanism for the core task in IMEs. The proposed neural P2C model is learned\nby encoding previous input utterance as extra context to enable our IME capable\nof predicting character sequence with incomplete pinyin input. Our model is\nevaluated in different benchmark datasets showing great user experience\nimprovement compared to traditional models, which demonstrates the first\nengineering practice of building Chinese aided IME.","url_abs":"http://arxiv.org/abs/1809.00329v1","url_pdf":"http://arxiv.org/pdf/1809.00329v1.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":"chinese-pinyin-aided-ime-input-what-you-have","repo_url":"https://github.com/YvonneHuang/gaIME","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.00329","atlas_url":"https://app.syntology.ai/?focus=1809.00329","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}