Abstract
This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2010 evaluation campaign. As part of these efforts, we experimented with a number of extensions to the standard phrase-based model that improve performance on the Arabic and Turkish to English translation tasks. We also participated in the new French to English BTEC and English to French TALK tasks. We discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2008 system, and experiments we ran during the IWSLT-2010 evaluation. Specifically, we focus on 1) cross-domain translation using MAP adaptation, 2) Turkish morphological processing and translation, 3) improved Arabic morphology for MT preprocessing, and 4) system combination methods for machine translation.- Anthology ID:
- 2010.iwslt-evaluation.16
- Volume:
- Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign
- Month:
- December 2-3
- Year:
- 2010
- Address:
- Paris, France
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 127–134
- Language:
- URL:
- https://aclanthology.org/2010.iwslt-evaluation.16
- DOI:
- Cite (ACL):
- Wade Shen, Timothy Anderson, Raymond Slyh, and A. Ryan Aminzadeh. 2010. The MIT-LL/AFRL IWSLT-2010 MT system. In Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 127–134, Paris, France.
- Cite (Informal):
- The MIT-LL/AFRL IWSLT-2010 MT system (Shen et al., IWSLT 2010)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2010.iwslt-evaluation.16.pdf