Multi-document Summarization via Deep Learning Techniques: A Survey

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. This survey, the first of its kind, systematically overviews the recent deep learning-based MDS models. This paper proposes a novel taxonomy to summarize the design strategies of neural networks and conduct a comprehensive summary of the state-of-the-art. In this paper, researchers have highlighted the differences between various objective functions that are rarely discussed in the existing literature. Finally, They propose several future directions pertaining to this new and exciting field.