Multi-document Summarization via Deep Learning Techniques: A Survey

TL;DR

This survey comprehensively reviews recent deep learning approaches for multi-document summarization, highlighting design strategies, objective functions, and future research directions in this rapidly evolving field.

Contribution

It introduces a novel taxonomy for neural network design strategies in deep learning-based MDS and provides a comprehensive summary of the latest models and their differences.

Findings

Systematic overview of recent deep learning MDS models

Identification of differences in objective functions used

Proposed future research directions in the field

Abstract

Multi-document summarization (MDS) is an effective tool for information aggregation that generates an informative and concise summary from a cluster of topic-related documents. Our survey, the first of its kind, systematically overviews the recent deep learning based MDS models. We propose a novel taxonomy to summarize the design strategies of neural networks and conduct a comprehensive summary of the state-of-the-art. We highlight the differences between various objective functions that are rarely discussed in the existing literature. Finally, we propose several future directions pertaining to this new and exciting field.