Detecting Novelty in the context of Progressive Summarization

A Progressive summary helps a user to monitor changes in evolving news topics over a period of time. Detecting novel information is the essential part of progressive summarization that differentiates it from normal multi document summarization. In this work, we explore the possibility of detecting novelty at various stages of summarization. New scoring features, Re-ranking criterions and filtering strategies are proposed to identify “relevant novel” information. We compare these techniques using an automated evaluation framework ROUGE, and determine the best. Overall, our summarizer is able to perform on par with existing prime methods in progressive summarization.