English

Semantic Graph Convolutional Network for Implicit Discourse Relation Classification

Computation and Language 2019-10-22 v1

Abstract

Implicit discourse relation classification is of great importance for discourse parsing, but remains a challenging problem due to the absence of explicit discourse connectives communicating these relations. Modeling the semantic interactions between the two arguments of a relation has proven useful for detecting implicit discourse relations. However, most previous approaches model such semantic interactions from a shallow interactive level, which is inadequate on capturing enough semantic information. In this paper, we propose a novel and effective Semantic Graph Convolutional Network (SGCN) to enhance the modeling of inter-argument semantics on a deeper interaction level for implicit discourse relation classification. We first build an interaction graph over representations of the two arguments, and then automatically extract in-depth semantic interactive information through graph convolution. Experimental results on the English corpus PDTB and the Chinese corpus CDTB both demonstrate the superiority of our model to previous state-of-the-art systems.

Keywords

Cite

@article{arxiv.1910.09183,
  title  = {Semantic Graph Convolutional Network for Implicit Discourse Relation Classification},
  author = {Yingxue Zhang and Ping Jian and Fandong Meng and Ruiying Geng and Wei Cheng and Jie Zhou},
  journal= {arXiv preprint arXiv:1910.09183},
  year   = {2019}
}

Comments

8 pages, 4 figures