Depthwise Separable Convolutions for Neural Machine Translation

ICLR 2018 Lukasz KaiserAidan N. GomezFrancois Chollet

Depthwise separable convolutions reduce the number of parameters and computation used in convolutional operations while increasing representational efficiency. They have been shown to be successful in image classification models, both in obtaining better models than previously possible for a given parameter count (the Xception architecture) and considerably reducing the number of parameters required to perform at a given level (the MobileNets family of architectures)... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Machine Translation WMT2014 English-German SliceNet BLEU score 26.1 # 14