Creating Multilingual Translation Lexicons with Regional Variations Using Web Corpora

Creating Multilingual Translation Lexicons with Regional Variations Using Web Corpora Pu-Jen Cheng*, Yi-Cheng Pan*, Wen-Hsiang Lu+, and Lee-Feng Chien* * Institute of Information Science, Academia Sinica, Taiwan + Dept. of Computer Science and Information Engineering, National Cheng Kung Univ., Taiwan Dept. of Information Management, National Taiwan University, Taiwan {pjcheng, thomas02, whlu, lfchien}@iis.sinica.edu.tw Abstract The purpose of this paper is to automatically create multilingual translation lexicons with regional variations. We propose a transitive translation approach to determine translation variations across languages that have insuffi- cient corpora for translation via the mining of bilingual search-result pages and clues of geographic information obtained from Web search engines. The experimental results have shown the feasibility of the proposed approach in efficiently generating translation equivalents of various terms not covered by general translation dictionaries. It also re- vealed that the created translation lexicons can reflect different cultural aspects across regions such as Taiwan, Hong Kong and mainland China. 1 Introduction Compilation of translation lexicons is a crucial proc- ess for machine translation (MT) (Brown et al., 1990) and cross-language information retrieval (CLIR) systems (Nie et al., 1999). A lot of effort has been spent on constructing translation lexicons from do- main-specific corpora in an automatic way (Melamed, 2000; Smadja et al., 1996; Kupiec, 1993). However, such methods encounter two fundamental problems: translation of regional variations and the lack of up-to-date and high-lexical-coverage corpus source, which are worthy of further investigation. The first problem is resulted from the fact that the translations of a term may have variations in dif- ferent dialectal regions. Translation lexicons con- structed with conventional methods may not adapt to regional usages. For example, a Chinese-English lexicon constructed using a Hong Kong corpus can- not be directly adapted to the use in mainland China and Taiwan. An obvious example is that the word “taxi” is normally translated into “的士” (Chinese transliteration of taxi) in Hong Kong, which is com- pletely different from the translated Chinese words of “出租车” (rental cars) in mainland China and “計 程車” (cars with meters) in Taiwan. Besides, trans- literations of a term are often pronounced differently across regions. For example, the company name “Sony” is transliterated into “新力” (xinli) in Tai- wan and “索尼” (suoni) in mainland China. Such terms, in today’s increasingly internationalized world, are appearing more and more often. It is be- lieved that their translations should reflect the cul- tural aspects across different dialectal regions. Translations without consideration of the regional usages will lead to many serious misunderstandings, especially if the context to the original terms is not available. Halpern (2000) discussed the importance of translating simplified and traditional Chinese lex- emes that are semantically, not orthographically, equivalent in various regions. However, previous work on constructing translation lexicons for use in different regions was limited. That might be resulted from the other problem that most of the conventional approaches are based heavily on domain-specific corpora. Such corpora may be insufficient, or un- available, for certain domains. The Web is becoming the largest data repository …

Content truncated to 500 words