AAAIDec, 2017

神经机器翻译的多通道编码器

TL;DRMulti-channel Encoder is proposed to improve Attention-based Encoder-Decoder architecture for neural machine translation by enhancing encoding components with different levels of composition, achieving a 6.52 BLEU point improvement on Chinese-English translation and BLEU=38.8 on the WMT14 English-French task.