Chinese Spelling Check based on Neural Machine Translation

Computational Linguistics and Chinese Language Processing Vol. 25, No. 1, June 2020, pp. 1-28 1  The Association for Computational Linguistics and Chinese Language Processing Chinese Spelling Check based on Neural Machine Translation Jhih-Jie Chen, Hai-Lun Tu, Ching-Yu Yang, Chiao-Wen Li and Jason S. Chang Abstract We present a method for Chinese spelling check that automatically learns to correct a sentence with potential spelling errors. In our approach, a character-based neural machine translation (NMT) model is trained to translate the potentially misspelled sentence into correct one, using right-and-wrong sentence pairs from newspaper edit logs and artificially generated data. The method involves extracting sentences contain edit of spelling correction from edit logs, using commonly confused right-and-wrong word pairs to generate artificial right-and-wrong sentence pairs in order to expand our training data , and training the NMT model. The evaluation on the United Daily News (UDN) Edit Logs and SIGHAN-7 Shared Task shows that adding artificial error data can significantly improve the performance of Chinese spelling check system. Keywords: Chinese Spelling Check, Artificial Error Generation, Neural Machine Translation, Edit Log 1. Introduction Spelling check is a common yet important task in natural language processing. It plays an important role in a wide range of applications such as word processors, assisted writing systems, and search engines. For example, search engine without spelling check is not user-friendly, while assisted writing system must perform spelling check as the minimal requirement. Web search engines such as Google (www.google.com) and Bing  Department of Computer Science, National Tsing-Hua University, Hsinchu, Taiwan Department of Library and Information Science, Research and Development Center for Physical Education, Health, and Information Technology, Fu Jen Catholic University, New Taipei, Taiwan  Department of Information System and Application, National Tsing-Hua University, Hsinchu, Taiwan E-mail: {jjc, helentu, chingyu, chiaowen, jason}@nlplab.cc 2 Jhih-Jie Chen et al (www.bing.com) typically perform spelling check on queries, in order to retrieve documents better meeting the user information need. The users’ queries would be corrected first by the spelling check component in order to avoid irrelevant or low-quality search results. In contrast to Web search engines, while Microsoft Word has a very effective spelling checker for English, there is still considerable room to improve the one for Chinese. Consider a sentence “他在文學方面有很高的造旨。” (‘He is highly accomplished in literature.’). In the context of this sentence, the character “旨” (pronounced ‘zhi’) is a typo. For another sentence “ 他 在 文 學 方 面 有 很 高 的 造 藝 。 ” , the character “ 藝 ” (pronounced ‘yi’) is also a typo. For these two typos, the correct character is “詣” (pronounced ‘yi’). Chinese spelling errors are due to two main reasons: one is similar sound (e.g., *藝 and 詣) and the other is similar shape (e.g., *旨 and 詣), as pointed by Liu et al. (2011). Unfortunately, such spelling error is probably uneasy to correct due to limited training data. In fact, there is a lack of training data for the Chinese spelling check task. Compared to western languages …

Content truncated to 500 words