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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Richardson, S., Dolan, W., Menezes, A., Pinkham, J.: Achieving commercial-quality translationwith example-based methods. In: Proceedings of MT Summit VIII (2001) 293–298
Menezes, A., Richardson, S.: A Best-first alignment algorithm for automatic extraction oftransfer mappings from bilingual corpora. In: Proceedings of the Workshop on Data-DrivenMachine Translation, ACL 2001 (2001) 39–46
Moore, R.: Towards a Simple and Accurate Statistical Approach to Learning TranslationRelationships Among Words. In: Proceedings of the Workshop on Data-Driven MachineTranslation, ACL 2001 (2001) 79–86
Menezes, A.: Better contextual translation using machine learning. In: Proceedings of theAMTA 2002 Conference (2002)
Heidorn, G. E.: Intelligent Writing Assistance. In: Dale, R., Moisl, H., Somers, H. (eds.): AHandbook of Natural Language Processing: Techniques and Applications for the Processingof Language as Text, Marcel Dekker, New York (2000) 181–207
Corston-Oliver, S., Gamon, M., Ringger, E., Moore, R.: An overview of Amalgam: a machine-learnedgeneration module. In: Proceedings of second International Natural LanguageGeneration Conference (INLG), Harriman, New York (2002)
Pinkham, J., Corston-Oliver, M., Smets, M., Pettenaro, M.: Rapid Assembly of a Large-scale French-English MT system. In: Proceedings of the MT Summit VIII (2001) 277–281
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dolan, W.B., Pinkham, J., Richardson, S.D. (2002). MSR-MT: The Microsoft Research Machine Translation System. In: Richardson, S.D. (eds) Machine Translation: From Research to Real Users. AMTA 2002. Lecture Notes in Computer Science(), vol 2499. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45820-4_27
Download citation
DOI: https://doi.org/10.1007/3-540-45820-4_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44282-0
Online ISBN: 978-3-540-45820-3
eBook Packages: Springer Book Archive