Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT

Wenjie Li, Ruifeng Yuan, Zili Wang

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


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 publicationThe 28th International Conference on Computational Linguistics (COLING’2020)
Publication statusPublished - 8 Dec 2020


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

Cite this