In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntactic and compositional-semantic representations of phrases and words in a dependency tree. Different with the original recursive neural network, we introduce the convolution and pooling layers, which can model a variety of compositions by the feature maps and choose the most informative compositions by the pooling layers. Based on RCNN, we use a discriminative model to re-rank a k-best list of candidate dependency parsing trees. The experiments show that RCNN is very effective to improve the state-of-the-art dependency parsing on both English and Chinese datasets.
@article{arxiv.1505.05667,
title = {A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network},
author = {Chenxi Zhu and Xipeng Qiu and Xinchi Chen and Xuanjing Huang},
journal= {arXiv preprint arXiv:1505.05667},
year = {2015}
}