Chinese-English Machine Translation System

Abstract We describe a Chinese to English Machine Translation system,developed,at the Johns Hopkins University for the NIST 2003 MT evaluation. The system is based on a Weighted Finite State Transducer implementation,of the alignment template translation model for statistical machine translation. The baseline MT system was trained using 100,000 sentence pairs selected from a static bitext training collection. Information retrieval techniques were then used to create specific training collections for each document,to be translated. This document-specific training set included bitext and name,entities that were then added to the baseline system by augmenting,the library of alignment templates. We report translation performance of baseline and IR-based systems on two NIST MT evaluation test sets. 1 Alignment Template Translation Model We first give an outline of the Alignment Template Translation Model (ATTM) (Och et al., 1999) for statistical machine,translation. The overall model,is based on a two-level alignment between,the source and the target sentence: a phrase-level alignment between,source and target phrases and a word-level alignment between words in these phrase pairs implemented,via individual alignment templates. The ATTM has been reformulated (Kumar and Byrne, 2003) so that both bitext word alignment and translation can be implementated,using standard weighted finite state transducer (WFST) operations