Evaluation of Domain Adaptation Techniques for TRANSLI in a Real-World Environment

Atefeh Farzindar, Wael Khreich


Abstract
Statistical Machine Translation (SMT) systems specialized for one domain often perform poorly when applied to other domains. Domain adaptation techniques allow SMT models trained from a source domain with abundant data to accommodate different target domains with limited data. This paper evaluates the performance of two adaptive techniques based on log-linear and mixture models on data from the legal domain in real-world settings. Performance evaluation includes post-editing time and effort required by a professional post-editor to improve the quality of machine-generated translations to meet industry standards, as well as traditional automated scoring techniques (BLEU scores). Results indicates that the domain adaptation techniques can yield a significant increase in BLEU score (up to three points) and a significant reduction in post-editing time of about one second per word in an operational environment.
Anthology ID:
2012.amta-commercial.6
Volume:
Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Commercial MT User Program
Month:
October 28-November 1
Year:
2012
Address:
San Diego, California, USA
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
Language:
URL:
https://aclanthology.org/2012.amta-commercial.6
DOI:
Bibkey:
Cite (ACL):
Atefeh Farzindar and Wael Khreich. 2012. Evaluation of Domain Adaptation Techniques for TRANSLI in a Real-World Environment. In Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Commercial MT User Program, San Diego, California, USA. Association for Machine Translation in the Americas.
Cite (Informal):
Evaluation of Domain Adaptation Techniques for TRANSLI in a Real-World Environment (Farzindar & Khreich, AMTA 2012)
Copy Citation:
PDF:
https://aclanthology.org/2012.amta-commercial.6.pdf