Compact Personalized Models for Neural Machine Translation

Joern Wuebker, Patrick Simianer, John DeNero


Abstract
We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models. We demonstrate that a large proportion of model parameters can be frozen during adaptation with minimal or no reduction in translation quality by encouraging structured sparsity in the set of offset tensors during learning via group lasso regularization. We evaluate this technique for both batch and incremental adaptation across multiple data sets and language pairs. Our system architecture–combining a state-of-the-art self-attentive model with compact domain adaptation–provides high quality personalized machine translation that is both space and time efficient.
Anthology ID:
D18-1104
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
881–886
Language:
URL:
https://aclanthology.org/D18-1104
DOI:
10.18653/v1/D18-1104
Bibkey:
Cite (ACL):
Joern Wuebker, Patrick Simianer, and John DeNero. 2018. Compact Personalized Models for Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 881–886, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Compact Personalized Models for Neural Machine Translation (Wuebker et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1104.pdf
Video:
 https://aclanthology.org/D18-1104.mp4