Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
This addresses the challenge of domain adaptation in machine translation when parallel corpora are scarce, offering a practical solution for real-world applications.
The paper tackles the problem of unsupervised domain adaptation for neural machine translation by proposing a framework that uses only target-language monolingual data to construct a datastore for k-nearest-neighbor retrieval, significantly improving translation accuracy on multi-domain datasets and achieving performance comparable to back-translation.
Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for $k$-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation.