Log In Sign Up

Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT

by   Ruifeng Yuan, et al.

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.


page 1

page 2

page 3

page 4


Summary Level Training of Sentence Rewriting for Abstractive Summarization

As an attempt to combine extractive and abstractive summarization, Sente...

Jointly Extracting and Compressing Documentswith Summary State Representations

We present a new neural model for text summarization that first extracts...

Jointly Extracting and Compressing Documents with Summary State Representations

We present a new neural model for text summarization that first extracts...

Neural Latent Extractive Document Summarization

Extractive summarization models need sentence level labels, which are us...

Abstractive Summarization Guided by Latent Hierarchical Document Structure

Sequential abstractive neural summarizers often do not use the underlyin...

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

Inspired by how humans summarize long documents, we propose an accurate ...

Exploring Explainable Selection to Control Abstractive Generation

It is a big challenge to model long-range input for document summarizati...