Neural Machine Translation in Linear Time

31 Oct 2016Nal KalchbrennerLasse EspeholtKaren SimonyanAaron van den OordAlex GravesKoray Kavukcuoglu

We present a novel neural network for processing sequences. The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the target sequence... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Machine Translation WMT2014 English-French ByteNet BLEU score 23.8 # 31
Machine Translation WMT2014 English-German ByteNet BLEU score 23.75 # 20
Machine Translation WMT2015 English-German ByteNet BLEU score 26.26 # 1