Simple and Scalable Nearest Neighbor Machine Translation

1 code implementation • 23 Feb 2023 • Yuhan Dai, Zhirui Zhang, Qiuzhi Liu, Qu Cui, Weihua Li, Yichao Du, Tong Xu

$k$NN-MT is a straightforward yet powerful approach for fast domain adaptation, which directly plugs pre-trained neural machine translation (NMT) models with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining.

Domain Adaptation Machine Translation +4