Finding Sparse Structures for Domain Specific Neural Machine Translation

By Jianze Liang, Chengqi Zhao, Mingxuan Wang, Xipeng Qiu, Lei Li. 2021

33 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yang Feng
2. Chenze Shao
3. Wai Lam
4. Shuhao Gu
5. Lidong Bing
6. Wanying Xie
7. Zihao Fu
8. Anthony Man-Cho So

In Computer Vision and Pattern Recognition

1. Yang Feng
2. Chenze Shao
3. Shuhao Gu
4. Wanying Xie
5. Wai Lam
6. Zihao Fu
7. Anthony Man-Cho So
8. Lidong Bing

Citations in the corpus

• Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation (2022, background): “Liang et al. (2021); Gu et al. (2021) fixed important parameters during the fine-tuning to preserve the general-domain performance.”
• Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation (2021, background): “Luong and Manning (2015) fine-tunes the general-domain model with the in-domain data.”
• On the Effectiveness of Parameter-Efficient Fine-Tuning (2022, background): “…works (Salman et al., 2020; Jiang et al., 2020; Li and Zhang, 2021; Hua et al., 2021) propose to train model adversarially while some researchers (You et al., 2019; Liang et al., 2021; Ansell et al., 2021; Chen et al., 2021) propose to utilize the lottery ticket approaches to prune the network.”