%0 Journal Article
%T Dependency-based Convolutional Neural Networks for Sentence Embedding
%A Mingbo Ma
%A Liang Huang
%A Bing Xiang
%A Bowen Zhou
%J Computer Science
%D 2015
%I arXiv
%X In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To exploit both deep learning and linguistic structures, we propose a tree-based convolutional neural network model which exploit various long-distance relationships between words. Our model improves the sequential baselines on all three sentiment and question classification tasks, and achieves the highest published accuracy on TREC.
%U http://arxiv.org/abs/1507.01839v2