GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Authors

  • Fuzhao Xue School of Computer Science and Engineering, Nanyang Technological University, Singapore
  • Aixin Sun School of Computer Science and Engineering, Nanyang Technological University, Singapore
  • Hao Zhang School of Computer Science and Engineering, Nanyang Technological University, Singapore Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore
  • Eng Siong Chng School of Computer Science and Engineering, Nanyang Technological University, Singapore

Keywords:

Information Extraction

Abstract

Relation Extraction (RE) is to predict the relation type of two entities that are mentioned in a piece of text, e.g., a sentence or a dialogue. When the given text is long, it is challenging to identify indicative words for the relation prediction. Recent advances on RE task are from BERT-based sequence modeling and graph-based modeling of relationships among the tokens in the sequence. In this paper, we propose to construct a latent multi-view graph to capture various possible relationships among tokens. We then refine this graph to select important words for relation prediction. Finally, the representation of the refined graph and the BERT-based sequence representation are concatenated for relation extraction. Specifically, in our proposed GDPNet (Gaussian Dynamic Time Warping Pooling Net), we utilize Gaussian Graph Generator (GGG) to generate edges of the multi-view graph. The graph is then refined by Dynamic Time Warping Pooling (DTWPool). On DialogRE and TACRED, we show that GDPNet achieves the best performance on dialogue-level RE, and comparable performance with the state-of-the-arts on sentence-level RE. Our code is available at https://github.com/XueFuzhao/GDPNet.

Downloads

Published

2021-05-18

How to Cite

Xue, F., Sun, A., Zhang, H., & Chng, E. S. (2021). GDPNet: Refining Latent Multi-View Graph for Relation Extraction. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), 14194-14202. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17670

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing III