English

A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network

Computation and Language 2015-05-22 v1 Machine Learning Neural and Evolutionary Computing

Abstract

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 kk-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.

Keywords

Cite

@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}
}
R2 v1 2026-06-22T09:38:38.064Z