A General Contextualized Rewriting Framework for Text Summarization

07/13/2022
by   Guangsheng Bao, et al.
0

The rewriting method for text summarization combines extractive and abstractive approaches, improving the conciseness and readability of extractive summaries using an abstractive model. Exiting rewriting systems take each extractive sentence as the only input, which is relatively focused but can lose necessary background knowledge and discourse context. In this paper, we investigate contextualized rewriting, which consumes the entire document and considers the summary context. We formalize contextualized rewriting as a seq2seq with group-tag alignments, introducing group-tag as a solution to model the alignments, identifying extractive sentences through content-based addressing. Results show that our approach significantly outperforms non-contextualized rewriting systems without requiring reinforcement learning, achieving strong improvements on ROUGE scores upon multiple extractors.

READ FULL TEXT
research
01/31/2021

Contextualized Rewriting for Text Summarization

Extractive summarization suffers from irrelevance, redundancy and incohe...
research
04/21/2017

Scientific Article Summarization Using Citation-Context and Article's Discourse Structure

We propose a summarization approach for scientific articles which takes ...
research
11/08/2019

Towards automatic extractive text summarization of A-133 Single Audit reports with machine learning

The rapid growth of text data has motivated the development of machine-l...
research
09/04/2019

An Entity-Driven Framework for Abstractive Summarization

Abstractive summarization systems aim to produce more coherent and conci...
research
10/11/2012

Artex is AnotheR TEXt summarizer

This paper describes Artex, another algorithm for Automatic Text Summari...
research
09/25/2018

BanditSum: Extractive Summarization as a Contextual Bandit

In this work, we propose a novel method for training neural networks to ...
research
09/08/2019

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses

Sentence position is a strong feature for news summarization, since the ...

Please sign up or login with your details

Forgot password? Click here to reset