Abstract
The Multi-Engine MT (MEMT) architecture combines the outputs of multiple MT engines using a statistical language model of the target language. It has been used successfully in a number of MT research systems, for both text and speech translation. Despite its perceived benefits, there has never been a rigorous, published, double-blind evaluation of the claim that the combined output of a MEMT system is in fact better than that of any one of the component MT engines. We report here the results of such an evaluation. The combined MEMT output is shown to indeed be better overall than the output of the component engines in a Croatian ↔ English MT system. This result is consistent in both translation directions, and between different raters.- Anthology ID:
- 1998.amta-papers.10
- Volume:
- Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers
- Month:
- October 28-31
- Year:
- 1998
- Address:
- Langhorne, PA, USA
- Editors:
- David Farwell, Laurie Gerber, Eduard Hovy
- Venue:
- AMTA
- SIG:
- Publisher:
- Springer
- Note:
- Pages:
- 113–123
- Language:
- URL:
- https://link.springer.com/chapter/10.1007/3-540-49478-2_11
- DOI:
- Cite (ACL):
- Christopher Hogan and Robert E. Frederking. 1998. An evaluation of the multi-engine MT architecture. In Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 113–123, Langhorne, PA, USA. Springer.
- Cite (Informal):
- An evaluation of the multi-engine MT architecture (Hogan & Frederking, AMTA 1998)
- PDF:
- https://link.springer.com/chapter/10.1007/3-540-49478-2_11