Structural Attention Neural Networks for improved sentiment analysis

Filippos Kokkinos, Alexandros Potamianos


Abstract
We introduce a tree-structured attention neural network for sentences and small phrases and apply it to the problem of sentiment classification. Our model expands the current recursive models by incorporating structural information around a node of a syntactic tree using both bottom-up and top-down information propagation. Also, the model utilizes structural attention to identify the most salient representations during the construction of the syntactic tree.
Anthology ID:
E17-2093
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
586–591
Language:
URL:
https://www.aclweb.org/anthology/E17-2093
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/E17-2093.pdf