%0 Conference Proceedings %T Structural Attention Neural Networks for improved sentiment analysis %A Kokkinos, Filippos %A Potamianos, Alexandros %Y Lapata, Mirella %Y Blunsom, Phil %Y Koller, Alexander %S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers %D 2017 %8 April %I Association for Computational Linguistics %C Valencia, Spain %F kokkinos-potamianos-2017-structural %X 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. %U https://aclanthology.org/E17-2093 %P 586-591