Multi-document Summarization via Deep Learning Techniques: A Survey
It offers a foundational overview for researchers in natural language processing, but is incremental as a survey rather than a new method.
This paper tackles the problem of multi-document summarization by providing a systematic survey of deep learning techniques, proposing a novel taxonomy and highlighting differences in objective functions.
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.