Abstract
This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2008 evaluation campaign. As part of these efforts, we experimented with a number of extensions to the standard phrase-based model that improve performance for both text and speech-based translation on Chinese and Arabic translation tasks. We discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2007 system, and experiments we ran during the IWSLT-2008 evaluation. Specifically, we focus on 1) novel segmentation models for phrase-based MT, 2) improved lattice and confusion network decoding of speech input, 3) improved Arabic morphology for MT preprocessing, and 4) system combination methods for machine translation.- Anthology ID:
- 2008.iwslt-evaluation.10
- Volume:
- Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign
- Month:
- October 20-21
- Year:
- 2008
- Address:
- Waikiki, Hawaii
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 69–76
- Language:
- URL:
- https://aclanthology.org/2008.iwslt-evaluation.10
- DOI:
- Cite (ACL):
- Wade Shen, Brian Delaney, Tim Anderson, and Ray Slyh. 2008. The MIT-LL/AFRL IWSLT-2008 MT system.. In Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 69–76, Waikiki, Hawaii.
- Cite (Informal):
- The MIT-LL/AFRL IWSLT-2008 MT system. (Shen et al., IWSLT 2008)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2008.iwslt-evaluation.10.pdf