Convolutional Sequence to Sequence Learning

ICML 2017 Jonas GehringMichael AuliDavid GrangierDenis YaratsYann N. Dauphin

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Machine Translation IWSLT2015 English-German ConvS2S BLEU score 26.73 # 5
Machine Translation IWSLT2015 German-English ConvS2S BLEU score 32.31 # 8
Machine Translation WMT2014 English-French ConvS2S (ensemble) BLEU score 41.29 # 7
Machine Translation WMT2014 English-French ConvS2S BLEU score 40.46 # 11
Machine Translation WMT2014 English-German ConvS2S BLEU score 25.16 # 12
Machine Translation WMT2014 English-German ConvS2S (ensemble) BLEU score 26.4 # 8
Machine Translation WMT2016 English-Romanian ConvS2S BPE40k BLEU score 29.88 # 1