Multi-document Summarization via Deep Learning Techniques: A Survey

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