Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

05/28/2018
by   Yen-Chun Chen, et al.
0

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall summary. We use a novel sentence-level policy gradient method to bridge the non-differentiable computation between these two neural networks in a hierarchical way, while maintaining language fluency. Empirically, we achieve the new state-of-the-art on all metrics (including human evaluation) on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores. Moreover, by first operating at the sentence-level and then the word-level, we enable parallel decoding of our neural generative model that results in substantially faster (10-20x) inference speed as well as 4x faster training convergence than previous long-paragraph encoder-decoder models. We also demonstrate the generalization of our model on the test-only DUC-2002 dataset, where we achieve higher scores than a state-of-the-art model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/19/2019

Summary Level Training of Sentence Rewriting for Abstractive Summarization

As an attempt to combine extractive and abstractive summarization, Sente...
research
05/16/2018

A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss

We propose a unified model combining the strength of extractive and abst...
research
04/05/2021

Efficient Attentions for Long Document Summarization

The quadratic computational and memory complexities of large Transformer...
research
05/04/2020

Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction

Automatic sentence summarization produces a shorter version of a sentenc...
research
11/19/2020

Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT

Most current extractive summarization models generate summaries by selec...
research
05/28/2022

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Sentence summarization aims at compressing a long sentence into a short ...
research
09/25/2018

BanditSum: Extractive Summarization as a Contextual Bandit

In this work, we propose a novel method for training neural networks to ...

Please sign up or login with your details

Forgot password? Click here to reset