@article{Liang_Zhao_Wang_Qiu_Li_2021, title={Finding Sparse Structures for Domain Specific Neural Machine Translation}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17574}, DOI={10.1609/aaai.v35i15.17574}, abstractNote={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.}, number={15}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liang, Jianze and Zhao, Chengqi and Wang, Mingxuan and Qiu, Xipeng and Li, Lei}, year={2021}, month={May}, pages={13333-13342} }