Simple Unsupervised Summarization by Contextual Matching

Abstract: We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two LLMs, 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.