Learning Kernel-Smoothed Machine Translation with Retrieved Examples
This addresses the challenge of updating deployed machine translation models for emerging cases, offering an incremental improvement over non-parametric retrieval-based approaches.
The paper tackles the problem of adapting neural machine translation models online without retraining by proposing KSTER, which improves BLEU scores by 1.1 to 1.5 over existing methods in domain adaptation and multi-domain datasets.
How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a challenge. Existing non-parametric approaches that retrieve similar examples from a database to guide the translation process are promising but are prone to overfit the retrieved examples. In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online. Experiments on domain adaptation and multi-domain machine translation datasets show that even without expensive retraining, KSTER is able to achieve improvement of 1.1 to 1.5 BLEU scores over the best existing online adaptation methods. The code and trained models are released at https://github.com/jiangqn/KSTER.