Discourse-Aware Unsupervised Summarization for Long Scientific Documents
Yue Dong, Andrei Mircea Romascanu, Jackie Chi Kit Cheung
Discourse and Pragmatics Long paper Paper
You can open the pre-recorded video in separate windows.
Abstract:
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymmetrical positional cues to determine sentence importance. Results on the PubMed and arXiv datasets show that our approach outperforms strong unsupervised baselines by wide margins in automatic metrics and human evaluation. In addition, it achieves performance comparable to many state-of-the-art supervised approaches which are trained on hundreds of thousands of examples. These results suggest that patterns in the discourse structure are a strong signal for determining importance in scientific articles.
NOTE: Video may display a random order of authors.
Correct author list is at the top of this page.