A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion

10/08/2020
by   Logan Lebanoff, et al.
0

We present an empirical study in favor of a cascade architecture to neural text summarization. Summarization practices vary widely but few other than news summarization can provide a sufficient amount of training data enough to meet the requirement of end-to-end neural abstractive systems which perform content selection and surface realization jointly to generate abstracts. Such systems also pose a challenge to summarization evaluation, as they force content selection to be evaluated along with text generation, yet evaluation of the latter remains an unsolved problem. In this paper, we present empirical results showing that the performance of a cascaded pipeline that separately identifies important content pieces and stitches them together into a coherent text is comparable to or outranks that of end-to-end systems, whereas a pipeline architecture allows for flexible content selection. We finally discuss how we can take advantage of a cascaded pipeline in neural text summarization and shed light on important directions for future research.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/06/2023

Towards End-to-end Speech-to-text Summarization

Speech-to-text (S2T) summarization is a time-saving technique for filter...
research
09/10/2019

Select and Attend: Towards Controllable Content Selection in Text Generation

Many text generation tasks naturally contain two steps: content selectio...
research
09/03/2018

Data-to-Text Generation with Content Selection and Planning

Recent advances in data-to-text generation have led to the use of large-...
research
04/08/2021

Nutribullets Hybrid: Multi-document Health Summarization

We present a method for generating comparative summaries that highlights...
research
10/24/2022

Controlled Text Reduction

Producing a reduced version of a source text, as in generic or focused s...
research
07/31/2020

An Empirical Study on Explainable Prediction of Text Complexity: Preliminaries for Text Simplification

Text simplification is concerned with reducing the language complexity a...
research
10/26/2016

Content Selection in Data-to-Text Systems: A Survey

Data-to-text systems are powerful in generating reports from data automa...

Please sign up or login with your details

Forgot password? Click here to reset