Abstract
We present a novel fusion model for domain adaptation in Statistical Machine Translation. Our model is based on the joint source-target neural network Devlin et al., 2014, and is learned by fusing in- and out-domain models. The adaptation is performed by backpropagating errors from the output layer to the word embedding layer of each model, subsequently adjusting parameters of the composite model towards the in-domain data. On the standard tasks of translating English-to-German and Arabic-to-English TED talks, we observed average improvements of +0.9 and +0.7 BLEU points, respectively over a competition grade phrase-based system. We also demonstrate improvements over existing adaptation methods.- Anthology ID:
- C16-1299
- Volume:
- Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Editors:
- Yuji Matsumoto, Rashmi Prasad
- Venue:
- COLING
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 3177–3187
- Language:
- URL:
- https://aclanthology.org/C16-1299
- DOI:
- Cite (ACL):
- Nadir Durrani, Hassan Sajjad, Shafiq Joty, and Ahmed Abdelali. 2016. A Deep Fusion Model for Domain Adaptation in Phrase-based MT. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3177–3187, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- A Deep Fusion Model for Domain Adaptation in Phrase-based MT (Durrani et al., COLING 2016)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/C16-1299.pdf