Word-Transliteration Alignment

Word-Transliteration Alignment Tracy Lin Dep. of Communication Engineering National Chiao Tung University, 1001, Ta Hsueh Road, Hsinchu, 300, Taiwan tracylin@cm.nctu.edu.tw Chien-Cheng Wu Department of Computer Science National Tsing Hua University 101, Kuangfu Road, Hsinchu, 300, Taiwan g904374@oz.nthu.edu.tw Jason S. Chang Department of Computer Science National Tsing Hua University 101, Kuangfu Road, Hsinchu, 300, Taiwan jschang@cs.nthu.edu.tw Abstract The named-entity phrases in free text represent a formidable challenge to text analysis. Translat- ing a named-entity is important for the task of Cross Language Information Retrieval and Ques- tion Answering. However, both tasks are not easy to handle because named-entities found in free text are often not listed in a monolingual or bilingual dictionary. Although it is possible to iden- tify and translate named-entities on the fly without a list of proper names and transliterations, an extensive list certainly will ensure the high accuracy rate of text analysis. We use a list of proper names and transliterations to train a Machine Transliteration Model. With the model it is possi- ble to extract proper names and their transliterations in a bilingual corpus with high average pre- cision and recall rates. 1. Introduction Multilingual named entity identification and (back) transliteration has been increasingly recognized as an important research area for many applications, including machine translation (MT), cross language in- formation retrieval (CLIR), and question answering (QA). These transliterated words are often domain- specific and many of them are not found in existing bilingual dictionaries. Thus, it is difficult to handle transliteration only via simple dictionary lookup. For CLIR, the accuracy of transliteration highly affects the performance of retrieval. Transliteration of proper names tends to be varied from translator to translator. Consensus on translit- eration of celebrated place and person names emerges over a short period of inconsistency and stays unique and unchanged thereafter. But for less known persons and unfamiliar places, the transliterations of names may vary a great deal. That is exacerbated by different systems used for Ramanizing Chinese or Japanese person and place names. For back transliteration task of converting many transliterations back to the unique original name, there is one and only solution. So back transliteration is considered more diffi- cult than transliteration. Knight and Graehl (1998) pioneered the study of machine transliteration and pro- posed a statistical transliteration model from English to Japanese to experiment on back transliteration of Japanese named entities. Most previous approaches to machine transliteration (Al-Onaizan and Knight, 2002; Chen et al., 1998; Lin and Chen, 2002); English/Japanese (Knight and Graehl, 1998; Lee and Choi, 1997; Oh and Choi, 2002) focused on the tasks of transliteration and back-transliteration. Very little has been touched upon for the issue of aligning and acquiring words and transliterations in a parallel corpus. The alternative to on-the-fly (back) machine transliteration is simple lookup in an extensive list auto- matically acquired from parallel corpora. Most instances of (back) transliteration of proper names can often be found in a parallel corpus of substantial size and relevant to the task. For instance, fifty topics of the …

Content truncated to 500 words