The NRC Publications Archive is now operational; however, not all the features of the site are available at this time.
The following features remain unavailable:
- Viewing/Downloading of full text publications
NRC is currently working to restore these features and we will update this notice as these features become available. Thank you for your patience.
Mixing multiple translation models in statistical machine translation
; Razmara, Majid
; Foster, George
; Sankaran, Baskaran
National Research Council Canada
50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), Jeju Island, Republic of Korea, 8-14 July, 2012
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics
Natural Language Processing; Traitement des langues naturelles
Interactive Language Technologies; Technologies langagières interactives
Statistical machine translation is often faced with the problem of combining training data from many diverse sources into a single translation
model which then has to translate sentences in a new domain. We propose a novel approach, ensemble decoding, which combines
a number of translation systems dynamically at the decoding step. In this paper, we evaluate performance on a domain adaptation setting where we translate sentences from the medical domain. Our experimental
results show that ensemble decoding outperforms various strong baselines including mixture models, the current state-of-the-art for domain
adaptation in machine translation.