Event Timeline Generation and Summarization using PageRank

Abstract

Given a search query our system retrieves most significant events related to the query and display them in user friendly timeline. We are using graph structure to compute relative importance of events. We are representing event and its elements as complete graph. To rank events we are linearly combining basic IR ranking and ranking of event elements. evaluation on DUC Data experimental results shows that our system performs at par with the NLP based summarization techniques and yet works as fast as a search engine