Phonological Context Approximation and Homophone Treatment for NEWS 2009 English-Chinese Transliteration Shared Task

Abstract

This paper describes our systems participating in the NEWS 2009 Machine Transliteration Shared Task. Two runs were submitted for the English-Chinese track. The system for the standard run is based on graphemic approximation of local phonological context. The one for the non-standard run is based on parallel modelling of sound and tone patterns for treating homophones in Chinese. Official results show that both systems stand in the mid range amongst all participating systems.