Weidong Liu


2024

pdf bib
Pluggable Neural Machine Translation Models via Memory-augmented Adapters
Yuzhuang Xu | Shuo Wang | Peng Li | Xuebo Liu | Xiaolong Wang | Weidong Liu | Yang Liu
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Although neural machine translation (NMT) models perform well in the general domain, it remains rather challenging to control their generation behavior to satisfy the requirement of different users. Given the expensive training cost and the data scarcity challenge of learning a new model from scratch for each user requirement, we propose a memory-augmented adapter to steer pretrained NMT models in a pluggable manner. Specifically, we construct a multi-granular memory based on the user-provided text samples and propose a new adapter architecture to combine the model representations and the retrieved results. We also propose a training strategy using memory dropout to reduce spurious dependencies between the NMT model and the memory. We validate our approach on both style- and domain-specific experiments and the results indicate that our method can outperform several representative pluggable baselines.