Recent Trends in Unsupervised Summarization
It provides a comprehensive overview for researchers and practitioners in natural language processing, but it is incremental as it synthesizes existing work rather than introducing novel findings.
This survey paper tackles the problem of summarizing recent trends in unsupervised summarization, covering various techniques, models, and a taxonomy without presenting new experimental results or concrete numbers.
Unsupervised summarization is a powerful technique that enables training summarizing models without requiring labeled datasets. This survey covers different recent techniques and models used for unsupervised summarization. We cover extractive, abstractive, and hybrid models and strategies used to achieve unsupervised summarization. While the main focus of this survey is on recent research, we also cover some of the important previous research. We additionally introduce a taxonomy, classifying different research based on their approach to unsupervised training. Finally, we discuss the current approaches and mention some datasets and evaluation methods.