Measuring Machine Translation Errors in New Domains

Ann Irvine, John Morgan, Marine Carpuat, Hal Daumé III, Dragos Munteanu


Abstract
We develop two techniques for analyzing the effect of porting a machine translation system to a new domain. One is a macro-level analysis that measures how domain shift affects corpus-level evaluation; the second is a micro-level analysis for word-level errors. We apply these methods to understand what happens when a Parliament-trained phrase-based machine translation system is applied in four very different domains: news, medical texts, scientific articles and movie subtitles. We present quantitative and qualitative experiments that highlight opportunities for future research in domain adaptation for machine translation.
Anthology ID:
Q13-1035
Volume:
Transactions of the Association for Computational Linguistics, Volume 1
Month:
Year:
2013
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
429–440
Language:
URL:
https://aclanthology.org/Q13-1035
DOI:
10.1162/tacl_a_00239
Bibkey:
Cite (ACL):
Ann Irvine, John Morgan, Marine Carpuat, Hal Daumé III, and Dragos Munteanu. 2013. Measuring Machine Translation Errors in New Domains. Transactions of the Association for Computational Linguistics, 1:429–440.
Cite (Informal):
Measuring Machine Translation Errors in New Domains (Irvine et al., TACL 2013)
Copy Citation:
PDF:
https://aclanthology.org/Q13-1035.pdf