Papers › Towards Robust k-Nearest-Neighbor Machine Translation

Towards Robust k-Nearest-Neighbor Machine Translation

17 Oct 2022arXiv:2210.08808archive 2025-07-28

Hui Jiang, Ziyao Lu, Fandong Meng, Chulun Zhou, Jie zhou, Degen Huang, Jinsong Su

k-Nearest-Neighbor Machine Translation (kNN-MT) becomes an important research direction of NMT in recent years. Its main idea is to retrieve useful key-value pairs from an additional datastore to modify translations without updating the NMT model. However, the underlying retrieved noisy pairs will dramatically deteriorate the model performance. In this paper, we conduct a preliminary study and find that this problem results from not fully exploiting the prediction of the NMT model. To alleviate the impact of noise, we propose a confidence-enhanced kNN-MT model with robust training. Concretely, we introduce the NMT confidence to refine the modeling of two important components of kNN-MT: kNN distribution and the interpolation weight. Meanwhile we inject two types of perturbations into the retrieved pairs for robust training. Experimental results on four benchmark datasets demonstrate that our model not only achieves significant improvements over current kNN-MT models, but also exhibits better robustness. Our code is available at https://github.com/DeepLearnXMU/Robust-knn-mt.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

deeplearnxmu/robust-knn-mt officialmentioned in paperpytorch report
njunlp/knn-box mentioned on GitHubpytorch report
cordercorder/knn-models pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Machine TranslationNMTTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections