The MIT-LL/AFRL IWSLT-2009 MT system
Wade Shen, Brian Delaney, A. Ryan Aminzadeh, Tim Anderson, Ray Slyh
Abstract
This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2009 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 discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2008 system, and experiments we ran during the IWSLT-2009 evaluation. Specifically, we focus on 1) Cross-domain translation using MAP adaptation and unsupervised training, 2) Turkish morphological processing and translation, 3) improved Arabic morphology for MT preprocessing, and 4) system combination methods for machine translation.- Anthology ID:
- 2009.iwslt-evaluation.11
- Volume:
- Proceedings of the 6th International Workshop on Spoken Language Translation: Evaluation Campaign
- Month:
- December 1-2
- Year:
- 2009
- Address:
- Tokyo, Japan
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 71–78
- Language:
- URL:
- https://aclanthology.org/2009.iwslt-evaluation.11
- DOI:
- Cite (ACL):
- Wade Shen, Brian Delaney, A. Ryan Aminzadeh, Tim Anderson, and Ray Slyh. 2009. The MIT-LL/AFRL IWSLT-2009 MT system. In Proceedings of the 6th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 71–78, Tokyo, Japan.
- Cite (Informal):
- The MIT-LL/AFRL IWSLT-2009 MT system (Shen et al., IWSLT 2009)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2009.iwslt-evaluation.11.pdf