Abstract
In this paper, we propose two extensions to the vector space model (VSM) adaptation technique (Chen et al., 2013b) for statistical machine translation (SMT), both of which result in significant improvements. We also systematically compare the VSM techniques to three mixture model adaptation techniques: linear mixture, log-linear mixture (Foster and Kuhn, 2007), and provenance features (Chiang et al., 2011). Experiments on NIST Chinese-to-English and Arabic-to-English tasks show that all methods achieve significant improvement over a competitive non-adaptive baseline. Except for the original VSM adaptation method, all methods yield improvements in the +1.7-2.0 BLEU range. Combining them gives further significant improvements of up to +2.6-3.3 BLEU over the baseline.- Anthology ID:
- 2014.amta-researchers.10
- Volume:
- Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track
- Month:
- October 22-26
- Year:
- 2014
- Address:
- Vancouver, Canada
- Editors:
- Yaser Al-Onaizan, Michel Simard
- Venue:
- AMTA
- SIG:
- Publisher:
- Association for Machine Translation in the Americas
- Note:
- Pages:
- 124–138
- Language:
- URL:
- https://aclanthology.org/2014.amta-researchers.10
- DOI:
- Cite (ACL):
- Boxing Chen, Roland Kuhn, and George Foster. 2014. A comparison of mixture and vector space techniques for translation model adaptation. In Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track, pages 124–138, Vancouver, Canada. Association for Machine Translation in the Americas.
- Cite (Informal):
- A comparison of mixture and vector space techniques for translation model adaptation (Chen et al., AMTA 2014)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2014.amta-researchers.10.pdf