A Joint Graph Model for Pinyin-to-Chinese Conversion with Typo Correction

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1512–1523, Baltimore, Maryland, USA, June 23-25 2014. c⃝2014 Association for Computational Linguistics A Joint Graph Model for Pinyin-to-Chinese Conversion with Typo Correction∗ Zhongye Jia and Hai Zhao† MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering, Shanghai Jiao Tong University 800 Dongchuan Road, Shanghai 200240, China jia.zhongye@gmail.com, zhaohai@cs.sjtu.edu.cn Abstract It is very import for Chinese language pro- cessing with the aid of an efficient input method engine (IME), of which pinyin- to-Chinese (PTC) conversion is the core part. Meanwhile, though typos are in- evitable during user pinyin inputting, ex- isting IMEs paid little attention to such big inconvenience. In this paper, motivated by a key equivalence of two decoding algo- rithms, we propose a joint graph model to globally optimize PTC and typo correction for IME. The evaluation results show that the proposed method outperforms both ex- isting academic and commercial IMEs. 1 Introduction 1.1 Chinese Input Method The daily life of Chinese people heavily depends on Chinese input method engine (IME), no matter whether one is composing an E-mail, writing an article, or sending a text message. However, ev- ery Chinese word inputted into computer or cell- phone cannot be typed through one-to-one map- ping of key-to-letter inputting directly, but has to go through an IME as there are thousands of Chi- nese characters for inputting while only 26 letter keys are available in the keyboard. An IME is an essential software interface that maps Chinese characters into English letter combinations. An ef- ∗This work was partially supported by the National Natu- ral Science Foundation of China (Grant No.60903119, Grant No.61170114, and Grant No.61272248), the National Ba- sic Research Program of China (Grant No.2013CB329401), the Science and Technology Commission of Shanghai Mu- nicipality (Grant No.13511500200), and the European Union Seventh Framework Program (Grant No.247619). †Corresponding author ficient IME will largely improve the user experi- ence of Chinese information processing. Nowadays most of Chinese IMEs are pinyin based. Pinyin is originally designed as the pho- netic symbol of a Chinese character (based on the standard modern Chinese, mandarin) , using Latin letters as its syllable notation. For example, the pinyin of the Chinese character “爱”(love) is “ài”. Most characters usually have unique pinyin rep- resentations, while a few Chinese characters may be pronounced in several different ways, so they may have multiple pinyin representations. The ad- vantage of pinyin IME is that it only adopts the pronunciation perspective of Chinese characters so that it is simple and easy to learn. But there are only less than 500 pinyin syllables in stan- dard modern Chinese, compared with over 6,000 commonly used Chinese characters, which leads to serious ambiguities for pinyin-to-character map- ping. Modern pinyin IMEs mostly use a “sentence- based” decoding technique (Chen and Lee, 2000) to alleviate the ambiguities. “Sentence based” means that IME generates a sequence of Chinese characters upon a sequence of …

Content truncated to 500 words