The Johns Hopkins University 2003 Chinese-English Machine Translation System

Download: PDF, slides.

“The Johns Hopkins University 2003 Chinese-English Machine Translation System” by W. Byrne, S. Khudanpur, W. Kim, S. Kumar, P. Pecina, P.Virga, P. Xu, and D. Yarowsky. In Machine Translation Summit IX, 2003, {The Association for Machine Translation in the Americas}.

Abstract

We describe a Chinese to English Machine Translation system developed at the Johns Hopkins University for the NIST 2003 MT evaluations. 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.

Download: PDF, slides.

BibTeX entry:

@inproceedings{mtsummit03,
   author = {W. Byrne and S. Khudanpur and W. Kim and S. Kumar and P.
	Pecina and P.Virga and P. Xu and D. Yarowsky},
   title = {{The Johns Hopkins University 2003 Chinese-English Machine
	Translation System}},
   booktitle = {{Machine Translation Summit IX}},
   pages = {(4 pages)},
   year = {2003},
   organization = {{The Association for Machine Translation in the Americas}}
}

Back to Bill Byrne publications.