Can Chinese Phonemes Improve Machine Transliteration?: A Comparative Study of English-to-Chinese Transliteration Models

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 658–667, Singapore, 6-7 August 2009. c⃝2009 ACL and AFNLP Can Chinese Phonemes Improve Machine Transliteration?: A Comparative Study of English-to-Chinese Transliteration Models Jong-Hoon Oh, Kiyotaka Uchimoto, and Kentaro Torisawa Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT) 3-5 Hikaridai Seika-cho, Soraku-gun, Kyoto 619-0289 Japan {rovellia,uchimoto,torisawa}@nict.go.jp Abstract Inspired by the success of English grapheme-to-phoneme research in speech synthesis, many researchers have pro- posed phoneme-based English-to-Chinese transliteration models. However, such ap- proaches have severely suffered from the errors in Chinese phoneme-to-grapheme conversion. To address this issue, we propose a new English-to-Chinese transliteration model and make system- atic comparisons with the conventional models. Our proposed model relies on the joint use of Chinese phonemes and their corresponding English graphemes and phonemes. Experiments showed that Chinese phonemes in our proposed model can contribute to the performance im- provement in English-to-Chinese translit- eration. 1 Introduction 1.1 Motivation Transliteration, i.e., phonetic translation, is com- monly used to translate proper names and techni- cal terms across languages. A variety of English- to-Chinese machine transliteration models has been proposed in the last decade (Meng et al., 2001; Gao et al., 2004; Jiang et al., 2007; Lee and Chang, 2003; Li et al., 2004; Li et al., 2007; Wan and Verspoor, 1998; Virga and Khudanpur, 2003). They can be categorized into those based on Chinese phonemes (Meng et al., 2001; Gao et al., 2004; Jiang et al., 2007; Lee and Chang, 2003; Wan and Verspoor, 1998; Virga and Khu- danpur, 2003) and those that don’t rely on Chinese phonemes (Li et al., 2004; Li et al., 2007). Inspired by the success of English grapheme-to- phoneme research in speech synthesis, many re- searchers have proposed phoneme-based English- to-Chinese transliteration models. In these ap- proaches, Chinese phonemes are generated from English graphemes or phonemes, and then the Chinese phonemes are converted into Chinese graphemes (or characters), where Chinese Pinyin strings1 are used for representing a syllable-level Chinese phoneme sequence. Despite its high ac- curacy in generating Chinese phonemes from En- glish, this approach has severely suffered from er- rors in Chinese phoneme-to-grapheme conversion, mainly caused by Chinese homophone confusion – one Chinese Pinyin string can correspond to sev- eral Chinese characters (Li et al., 2004). For ex- ample, the Pinyin string “LI” corresponds to such different Chinese characters as �, �, and �. For this reason, it has been reported that English-to- Chinese transliteration without Chinese phonemes outperforms that with Chinese phonemes (Li et al., 2004). Then “Can Chinese phonemes improve English-to-Chinese transliteration, if we can re- duce the errors in Chinese phoneme-to-grapheme conversion?” Our research starts from this question. 1.2 Our Approach Previous approaches using Chinese phonemes have relied only on Chinese phonemes in Chi- nese phoneme-to-grapheme conversion. However, the simple use of Chinese phonemes doesn’t al- ways provide a good clue to reduce the ambi- guity in Chinese phoneme-to-grapheme conver- sion. Let us explain with an example, the Chinese transliteration of …

Content truncated to 500 words