A Convolutional Encoder Model for Neural Machine Translation

ACL 2017 Jonas GehringMichael AuliDavid GrangierYann N. Dauphin

The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper we present a faster and simpler architecture based on a succession of convolutional layers... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Machine Translation IWSLT2015 German-English Conv-LSTM (deep+pos) BLEU score 30.4 # 8
Machine Translation WMT2014 English-French Deep Convolutional Encoder; single-layer decoder BLEU score 35.7 # 25
Machine Translation WMT2016 English-Romanian BiLSTM BLEU score 27.5 # 12
Machine Translation WMT2016 English-Romanian Deep Convolutional Encoder; single-layer decoder BLEU score 27.8 # 11

Methods used in the Paper