Joint Source-Target Self Attention with Locality Constraints

16 May 2019José A. R. FonollosaNoe CasasMarta R. Costa-jussà

The dominant neural machine translation models are based on the encoder-decoder structure, and many of them rely on an unconstrained receptive field over source and target sequences. In this paper we study a new architecture that breaks with both conventions... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Machine Translation IWSLT2014 German-English Local Joint Self-attention BLEU score 35.7 # 2
Machine Translation WMT2014 English-French Local Joint Self-attention BLEU score 43.3 # 4
Machine Translation WMT2014 English-German Local Joint Self-attention BLEU score 29.7 # 9