神经机器翻译一句话一模型

Sep, 2016

One Sentence One Model for Neural Machine Translation

Xiaoqing Li, Jiajun Zhang, Chengqing Zong

TL;DR本篇论文提出了动态神经机器翻译(Dynamic NMT)的方法，通过对测试句子进行微调以适应具体场景，从而显着提高翻译性能。该方法特别适用于高度相似的句子。

Abstract

neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus