Explicitly Modeling Importance and Coherence for Timeline Summarization

Abstract

Timeline summarization (TLS) identifies major events and generates short summaries on how the event evolves in a period of time. Existing timeline summarization methods generate summaries by considering the coverage and diversity of the content and temporized information but ignore the importance and coherence of sentences used in summary. However, ignoring such information often causes missing important facts in the generated TLS and confuses users. We propose a better approach for TLS by explicitly optimizing importance and coherence on top of coverage and diversity. We apply our approach to both direct and pipeline TLS frameworks. Experimental results show that our approach achieves better performance when compared with two state-of-the-art TLS methods.

Bipartite Graph Pre-training for Unsupervised Extractive Summarization with Graph Convolutional Auto-Encoders

“…Traditional extractive summarization methods are mostly unsupervised (Yin and Pei, 2015;Nallapati et al, 2017;Zheng and Lapata, 2019;Zhong et al, 2019;Mao et al, 2022). Among them, graphbased sentential ranking methods are widely used.…”