Explicitly Modeling Importance and Coherence for Timeline Summarization

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 \textit{coverage} and \textit{diversity} of the content and temporized information but ignore the \textit{importance} and \textit{coherence} of sentences used in summary. However, ignoring such information often misses 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 to two state-of-the-art TLS methods.