BriefGPT.xyz
Feb, 2024
用扰动的kNN-MT生成多样化的翻译
Generating Diverse Translation with Perturbed kNN-MT
HTML
PDF
Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe
TL;DR
通过引入扰动k最近邻机器翻译（kNN-MT）方法，本文提出了一种生成更多样化翻译的方法，解决了过校正问题，改善了候选翻译的多样性，并通过调整扰动的幅度来控制多样性程度。
Abstract
Generating
multiple translation candidates
would enable users to choose the one that satisfies their needs. Although there has been work on
diversified generation
, there exists room for improving the diversity ma
→