A Survey on Neural Network-Based Summarization Methods

TL;DR

This paper reviews recent neural network-based methods for automatic text summarization, highlighting advances in abstractive and extractive models and discussing future research directions.

Contribution

It provides a comprehensive survey of ten state-of-the-art neural summarization models and related techniques, offering insights into current trends and challenges.

Findings

Neural models have significantly improved summarization quality.

Abstractive and extractive approaches each have unique strengths.

Future research should focus on hybrid models and better evaluation metrics.

Abstract

Automatic text summarization, the automated process of shortening a text while reserving the main ideas of the document(s), is a critical research area in natural language processing. The aim of this literature review is to survey the recent work on neural-based models in automatic text summarization. We examine in detail ten state-of-the-art neural-based summarizers: five abstractive models and five extractive models. In addition, we discuss the related techniques that can be applied to the summarization tasks and present promising paths for future research in neural-based summarization.