An entropy-regularized dynamic memory network with multimodal attention improves answers on the DSTC7 audio-visual scene-aware dialogue task.
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
-
Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
An entropy-regularized dynamic memory network with multimodal attention improves answers on the DSTC7 audio-visual scene-aware dialogue task.