A Survey of Automatic Text Summarization Technology Based on Deep Learning
Mengli Zhang, Gang Zhou, Wanting Yu, Wenfen Liu · 2020
With the rapid development of the Internet, the amount of network text data is increasing day by day. It is increasingly becoming a challenge to quickly mine useful information from massive amounts of text data. The emergence of automatic summarization technology provides new ideas and methods for solving this problem. Compared with extractive summarization model, abstractive summarization model more closely resembles the process of human summarization, giving it important research significance. In recent years, with the development of deep learning methods, text summarization technology based on deep learning has made unprecedented breakthroughs. Based on the current mainstream sequence-to- sequence framework, we summarize the state-of-the-art abstractive summarization models, compare the advantages of different models and applicable scenarios, and provide a clear context for researchers in related fields. Furthermore, we also make statistics on the Chinese and English datasets. Finally, we put forward some thoughts on the common problems in the field of automatic text summarization.