Interactive, domain-independent identification and summarization of topically related news articles

Abstract. In this paper we present NewsInEssence, a fully deployed digital news system. A user selects a current news story of interest which is used as a seed article by NewsInEssence to find in real time other related stories from a large number of news sources. The output is a single document summary presenting the most salient information gleaned from the different sources. We discuss the algorithm used by NewsInEssence, module interoperability, and conclude the paper with a number of empirical analyses. 1 Introduction Text summarization[10] is used to provide concise versions of text documents to a user who may not have the time to read the entire source material. A large amount of research has been devoted to the automatic generation of summaries of single documents. In this paper we extend the concept of a summary in three ways- our input contains many sources, many documents, and many time points. A news event is widely reported in the press. A large number of journalists independently pick a newsworthy piece and turn it into a sequence of news stories. We are concerned with the automatic generation of summaries of news events as they occur. In the generic scenario for our system, NewsInEssence, a user selects a single news story from a news Web site. Our system then searches other live sources of news for other stories related to the same event and produces summaries of a subset of the stories that it finds, as specified by the user