A tree-structured memory network that uses parse trees and distinguishes visual from verbal words improves video question answering accuracy over flat sequence attention baselines.
Tree-to-Sequence Attentional Neural Machine Translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Most of the existing Neural Machine Translation (NMT) models focus on the conversion of sequential data and do not directly use syntactic information. We propose a novel end-to-end syntactic NMT model, extending a sequence-to-sequence model with the source-side phrase structure. Our model has an attention mechanism that enables the decoder to generate a translated word while softly aligning it with phrases as well as words of the source sentence. Experimental results on the WAT'15 English-to-Japanese dataset demonstrate that our proposed model considerably outperforms sequence-to-sequence attentional NMT models and compares favorably with the state-of-the-art tree-to-string SMT system.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Better Way to Attend: Attention with Trees for Video Question Answering
A tree-structured memory network that uses parse trees and distinguishes visual from verbal words improves video question answering accuracy over flat sequence attention baselines.