pith. sign in

arxiv: 2012.10586 · v2 · pith:3ZIDU3NGnew · submitted 2020-12-19 · 💻 cs.CL · cs.AI

Finding Sparse Structures for Domain Specific Neural Machine Translation

classification 💻 cs.CL cs.AI
keywords domainprune-tunedomainsfine-tuningdomain-specificgeneralmachinemultiple
0
0 comments X
read the original abstract

Neural machine translation often adopts the fine-tuning approach to adapt to specific domains. However, nonrestricted fine-tuning can easily degrade on the general domain and over-fit to the target domain. To mitigate the issue, we propose Prune-Tune, a novel domain adaptation method via gradual pruning. It learns tiny domain-specific sub-networks during fine-tuning on new domains. Prune-Tune alleviates the over-fitting and the degradation problem without model modification. Furthermore, Prune-Tune is able to sequentially learn a single network with multiple disjoint domain-specific sub-networks for multiple domains. Empirical experiment results show that Prune-Tune outperforms several strong competitors in the target domain test set without sacrificing the quality on the general domain in both single and multi-domain settings. The source code and data are available at https://github.com/ohlionel/Prune-Tune.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.