Graph-based neural multi-document summarization

Michihiro Yasunaga, Rui Zhang, Kshitijh Meelu, Ayush Pareek, Krishnan Srinivasan, Dragomir Radev

Research output: Chapter in Book/Report/Conference proceedingConference contribution

78 Scopus citations

Abstract

We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use a greedy heuristic to extract salient sentences while avoiding redundancy. In our experiments on DUC 2004, we consider three types of sentence relation graphs and demonstrate the advantage of combining sentence relations in graphs with the representation power of deep neural networks. Our model improves upon traditional graph-based extractive approaches and the vanilla GRU sequence model with no graph, and it achieves competitive results against other state-of-the-art multidocument summarization systems.

Original languageEnglish (US)
Title of host publicationCoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages452-462
Number of pages11
ISBN (Electronic)9781945626548
DOIs
StatePublished - 2017
Event21st Conference on Computational Natural Language Learning, CoNLL 2017 - Vancouver, Canada
Duration: Aug 3 2017Aug 4 2017

Publication series

NameCoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings

Conference

Conference21st Conference on Computational Natural Language Learning, CoNLL 2017
Country/TerritoryCanada
CityVancouver
Period8/3/178/4/17

All Science Journal Classification (ASJC) codes

  • Linguistics and Language
  • Artificial Intelligence
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Graph-based neural multi-document summarization'. Together they form a unique fingerprint.

Cite this