Finding Sparse Structure for Domain Specific Neural Machine Translation

12/19/2020 ∙ by Jianze Liang, et al. ∙ 0

Fine-tuning is a major approach for domain adaptation in Neural Machine Translation (NMT). However, unconstrained fine-tuning requires very careful hyper-parameter tuning otherwise it is easy to fall into over-fitting on the target domain and degradation on the general domain. To mitigate it, we propose PRUNE-TUNE, a novel domain adaptation method via gradual pruning. It learns tiny domain-specific subnetworks for tuning. During adaptation to a new domain, we only tune its corresponding subnetwork. PRUNE-TUNE alleviates the over-fitting and the degradation problem without model modification. Additionally, with no overlapping between domain-specific subnetworks, PRUNE-TUNE is also capable of sequential multi-domain learning. Empirical experiment results show that PRUNE-TUNE outperforms several strong competitors in the target domain test set without the quality degradation of the general domain in both single and multiple domain settings.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 7

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.