A hybrid back-transliteration system for Japanese
A hybrid back-transliteration system for Japanese
复制标题
日语混合回译系统
DOI：
10.3115/1220355.1220441
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Hozumi Tanaka
中科院分区：
文献类型：
--
作者：
Slaven Bilac;Hozumi Tanaka
从一种语言到另一种语言的单词和名称的音译是一种频繁和高生产力的现象。音译是信息丢失，因为重要的区别在这个过程中没有保留。因此，自动将音译单词转换回其原始形式是一个真实的挑战。此外，由于其在MT和CLIR中的广泛适用性，从实践的角度来看，这是一个有趣的问题。在本文中，我们提出了一种新的方法，结合音译字符串分割模块与基于音素和基于字素的音译模块，以提高日语单词的回译。我们的实验表明，混合方法取得了显着的改善。
Transliterating words and names from one language to another is a frequent and highly productive phenomenon. Transliteration is information losing since important distinctions are not preserved in the process. Hence, automatically converting transliterated words back into their original form is a real challenge. In addition, due to its wide applicability in MT and CLIR, it is an interesting problem from a practical point of view. In this paper, we propose a new method, combining the transliterated string segmentation module with phoneme-based and grapheme-based transliteration modules in order to enhance the back-transliterations of Japanese words. Our experiments show significant improvements achieved by the hybrid approach.