Capsule routing after multi-head attention gives small consistent BLEU improvements over Transformer in NMT, with EM routing slightly better than dynamic routing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Multi-Head Attention with Capsule Networks
Capsule routing after multi-head attention gives small consistent BLEU improvements over Transformer in NMT, with EM routing slightly better than dynamic routing.