The Rule of Three: Abstractive Text Summarization in Three Bullet Points

TL;DR

This paper introduces a neural network model for abstractive text summarization that explicitly considers information structure by using three-bullet summaries, leading to improved control and performance.

Contribution

It proposes a novel neural network approach that explicitly models the information structure in three-bullet summaries, addressing limitations of previous models.

Findings

Controlled information structure improves summarization quality

Using three-bullet summaries aids analysis of information flow

Model outperforms previous approaches on structured summaries

Abstract

Neural network-based approaches have become widespread for abstractive text summarization. Though previously proposed models for abstractive text summarization addressed the problem of repetition of the same contents in the summary, they did not explicitly consider its information structure. One of the reasons these previous models failed to account for information structure in the generated summary is that standard datasets include summaries of variable lengths, resulting in problems in analyzing information flow, specifically, the manner in which the first sentence is related to the following sentences. Therefore, we use a dataset containing summaries with only three bullet points, and propose a neural network-based abstractive summarization model that considers the information structures of the generated summaries. Our experimental results show that the information structure of a summary can be controlled, thus improving the performance of the overall summarization.