Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers
EMNLP, pp. 1784-1795, 2020.
Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge weights measured by sentence similarities. In this work, we find that transformer attentions can be used to rank sente...More
PPT (Upload PPT)