Oct, 2023
knn-seq: 高效,可扩展的 kNN-MT 框架
knn-seq: Efficient, Extensible kNN-MT Framework
Hiroyuki Deguchi, Hayate Hirano, Tomoki Hoshino, Yuto Nishida, Justin Vasselli...
TL;DRk-nearest-neighbor machine translation improves neural machine translation by utilizing a vector database of translation examples, and the paper presents an efficient framework called knn-seq to handle large datasets.