Gated lexical shortcut connections added to the transformer yield 0.9 BLEU average gains on five WMT directions while lowering the lexical content stored in hidden states.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2019 2representative citing papers
A multimodal Transformer ingests image features plus multiple external entity label sources and learns to control their appearance in fluent output captions.
citing papers explorer
-
Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts
Gated lexical shortcut connections added to the transformer yield 0.9 BLEU average gains on five WMT directions while lowering the lexical content stored in hidden states.
-
Informative Image Captioning with External Sources of Information
A multimodal Transformer ingests image features plus multiple external entity label sources and learns to control their appearance in fluent output captions.