Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT

Ruifeng Yuan, Zili Wang, Wenjie Li

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

9 Citations (Scopus)

Abstract

Most current extractive summarization models generate summaries by selecting salient sentences. However, one of the problems with sentence-level extractive summarization is that there exists a gap between the human-written gold summary and the oracle sentence labels. In this paper, we propose to extract fact-level semantic units for better extractive summarization. We also introduce a hierarchical structure, which incorporates the multi-level of granularities of the textual information into the model. In addition, we incorporate our model with BERT using a hierarchical graph mask. This allows us to combine BERT’s ability in natural language understanding and the structural information without increasing the scale of the model. Experiments on the CNN/DaliyMail dataset show that our model achieves state-of-the-art results.

Original languageEnglish
Title of host publicationCOLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference
EditorsDonia Scott, Nuria Bel, Chengqing Zong
PublisherAssociation for Computational Linguistics (ACL)
Pages5629-5639
Number of pages11
ISBN (Electronic)9781952148279
Publication statusPublished - 2020
Event28th International Conference on Computational Linguistics, COLING 2020 - Virtual, Online, Spain
Duration: 8 Dec 202013 Dec 2020

Publication series

NameCOLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

Conference

Conference28th International Conference on Computational Linguistics, COLING 2020
Country/TerritorySpain
CityVirtual, Online
Period8/12/2013/12/20

ASJC Scopus subject areas

  • Computer Science Applications
  • Computational Theory and Mathematics
  • Theoretical Computer Science

Fingerprint

Dive into the research topics of 'Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT'. Together they form a unique fingerprint.

Cite this