Simple Unsupervised Summarization by Contextual Matching
This addresses the problem of generating summaries without labeled data for researchers in NLP, though it appears incremental as it builds on existing language modeling techniques.
The authors tackled unsupervised sentence summarization by using two language models—one generic and one domain-specific—with a product-of-experts approach to maintain context and fluency, achieving promising results on abstractive and extractive datasets without paired data.
We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by using a product-of-experts criteria these are enough for maintaining continuous contextual matching while maintaining output fluency. Experiments on both abstractive and extractive sentence summarization data sets show promising results of our method without being exposed to any paired data.