Papers › What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation

What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation

8 Nov 2022arXiv:2211.04052archive 2025-07-28

Wenhao Zhu, ShuJian Huang, Yunzhe Lv, Xin Zheng, Jiajun Chen

kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus. As a result, the constructed datastore is usually large and possibly redundant. In this paper, we investigate the interpretability issue of this approach: what knowledge does the NMT model need? We propose the notion of local correctness (LAC) as a new angle, which describes the potential translation correctness for a single entry and for a given neighborhood. Empirical study shows that our investigation successfully finds the conditions where the NMT model could easily fail and need related knowledge. Experiments on six diverse target domains and two language-pairs show that pruning according to local correctness brings a light and more explainable memory for kNN-MT domain adaptation.

PaperPDFCode

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

Code

njunlp/knn-box mentioned on GitHubpytorch 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

Domain AdaptationNMTTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pruningfail

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