DeepAI
Log In Sign Up

Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT

11/19/2020
by   Ruifeng Yuan, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

09/19/2019

Summary Level Training of Sentence Rewriting for Abstractive Summarization

As an attempt to combine extractive and abstractive summarization, Sente...
04/03/2019

Jointly Extracting and Compressing Documentswith Summary State Representations

We present a new neural model for text summarization that first extracts...
04/03/2019

Jointly Extracting and Compressing Documents with Summary State Representations

We present a new neural model for text summarization that first extracts...
08/22/2018

Neural Latent Extractive Document Summarization

Extractive summarization models need sentence level labels, which are us...
11/17/2022

Abstractive Summarization Guided by Latent Hierarchical Document Structure

Sequential abstractive neural summarizers often do not use the underlyin...
05/28/2018

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

Inspired by how humans summarize long documents, we propose an accurate ...
04/24/2020

Exploring Explainable Selection to Control Abstractive Generation

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