# Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT

arXiv: https://arxiv.org/abs/2011.09739 · HTML: https://mlsanity.com/paper/2011.09739/

## Key facts

- Cited by 4 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 4 of 4)

- [Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization](https://mlsanity.com/paper/2108.11846/) (2021)
- [TSTR: Too Short to Represent, Summarize with Details! Intro-Guided Extended Summary Generation](https://mlsanity.com/paper/2206.00847/) (2022)
- [Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architectures](https://mlsanity.com/paper/2204.11190/) (2022)
- [Generating Tips from Song Reviews: A New Dataset and Framework](https://mlsanity.com/paper/2205.06985/) (2022)

## Abstract (arXiv)

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.