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
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 429–440
- Language:
- URL:
- https://aclanthology.org/Q13-1035
- DOI:
- 10.1162/tacl_a_00239
- 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)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/Q13-1035.pdf