Abstract: 

Nowadays, online news articles are one of the most commonly accessed documents on the Web. However, due to the large amount of news articles available online, it is getting difficult for users to effectively search, understand, and track news stories.  To solve this problem, a research area of TimeLine Summarization (TLS) has been established, aiming to help users better understand the news landscape. In this talk, we discuss a novel task, Multiple TimeLine Summarization (MTLS), which extends the flexibility and versatility of Time-Line Summarization (TLS). Given a collection of time-stamped news articles, MTLS automatically discovers different important stories, and generates a corresponding timeline for each story. To achieve this, we proposed a novel unsupervised summarization framework based on two-stage affinity propagation. We also introduce a quantitative evaluation measure for MTLS based on extending the previous TLS evaluation methods.