Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation
By Shuhao Gu, Yang Feng, Wanying Xie. 2021
33 citations recorded by the source corpus.
Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both general domain and in-domain data. However, the existing methods for domain adaptation usually suffer from catastrophic forgetting, large domain divergence, and model explosion. To address these three problems, we propose a method of “divide and conquer” which is based on the importance of neurons or parameters for the translation model. In this method, we first prune the model and only keep the important neurons or parameters, making them responsible for both general-domain and in-domain translation. Then we further train the pruned model supervised by the original whole model with knowledge distillation. Last we expand the model to the original size and fine-tune the added parameters for the in-domain translation. We conducted experiments on different language pairs and domains and the results show that our method can achieve significant improvements compared with several strong baselines.
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
In Computer Vision and Pattern Recognition
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.”