MSR-MT: the Microsoft research machine translation system

Willaim B. Dolan, Jessie Pinkham, Stephen D. Richardson


Abstract
MSR-MT is an advanced research MT prototype that combines rule-based and statistical techniques with example-based transfer. This hybrid, large-scale system is capable of learning all its knowledge of lexical and phrasal translations directly from data. MSR-MT has undergone rigorous evaluation showing that, trained on a corpus of technical data similar to the test corpus, its output surpasses the quality of best-of-breed commercial MT systems.
Anthology ID:
2002.amta-systems.6
Volume:
Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: System Descriptions
Month:
October 8-12
Year:
2002
Address:
Tiburon, USA
Venue:
AMTA
SIG:
Publisher:
Springer
Note:
Pages:
237–239
Language:
URL:
https://link.springer.com/chapter/10.1007/3-540-45820-4_27
DOI:
Bibkey:
Copy Citation:
PDF:
https://link.springer.com/chapter/10.1007/3-540-45820-4_27