Skip to main navigation Skip to search Skip to main content

An encoder-decoder architecture with graph convolutional networks for abstractive summarization

  • Gangmin Li
  • , QiAo Yuan
  • , Pin Ni
  • , Junru Liu
  • , Xiangzhi Tong
  • , Hanzhe Lu
  • , Steven Guan
  • The University of Auckland
  • Xi'an Jiaotong-Liverpool University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)
2 Downloads (Pure)

Abstract

We propose a single-document abstractive summarization system that integrates token relation into a traditional RNN-based encoder-decoder architecture. We employ pointer-wise mutual information to represent the token relation and adopt Graph Convolutional Networks (GCN) to extract token representation from the relation graph. In our experiment on Gigaword, we consider importing two kinds of structural information: token (node) representation from the relation graph. Also, we implement two kinds of GCNs, a spectral-based one and a spatial-based one, to extract structural information. The result shows that the spatial based GCN-enhanced model with node representation outperforms the classical RNN-based encoder-decoder model.
Original languageEnglish
Title of host publication2021 IEEE 4th International Conference on Big Data and Artificial Intelligence, BDAI 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages91-97
Number of pages7
ISBN (Electronic)9781665412704
ISBN (Print)9781665412704
DOIs
Publication statusPublished - 20 Aug 2021
Event2021 IEEE 4th International Conference on Big Data and Artificial Intelligence (BDAI) - Qingdao
Duration: 2 Jul 20214 Jul 2021

Publication series

Name2021 IEEE 4th International Conference on Big Data and Artificial Intelligence, BDAI 2021

Conference

Conference2021 IEEE 4th International Conference on Big Data and Artificial Intelligence (BDAI)
CityQingdao
Period2/07/214/07/21
Other2021 IEEE 4th International Conference on Big Data and Artificial Intelligence (BDAI) (02/07/2021-04/07/2021, Qingdao)

Keywords

  • GCN
  • Natural language processing
  • Seq2Seq
  • text summarization
  • natural language processing

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems and Management
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'An encoder-decoder architecture with graph convolutional networks for abstractive summarization'. Together they form a unique fingerprint.

Cite this