Abstract
This paper presents a hybrid approach to English-Korean name transliteration. The base system is built on MOSES with enabled factored translation features. We expand the base system by combining with various transliteration methods including a Web-based n-best re-ranking, a dictionary-based method, and a rule-based method. Our standard run and best nonstandard run achieve 45.1 and 78.5, respectively, in top-1 accuracy. Experimental results show that expanding training data size significantly contributes to the performance. Also we discover that the Web-based re-ranking method can be successfully applied to the English-Korean transliteration.
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
Cite
CITATION STYLE
Hong, G., Kim, M. J., Lee, D. G., & Rim, H. C. (2009). A hybrid approach to English-Korean name transliteration. In NEWS 2009 - 2009 Named Entities Workshop: Shared Task on Transliteration at the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 (pp. 108–111). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1699705.1699733
Readers' Seniority
Readers' Discipline
