Techniques for automatically generating biographical summaries from news articles

Abstract

The work of manually creating a biographical summary from multiple information sources is both time-intensive and detail-oriented. Automating the task is also non-trivial because of the many NLP areas that must be used to efficiently extract the relevant facts. Yet, no study has been done to determine how powerful a biographical summarization system must be in order to achieve the basic goal of filling slots in a biography template. Equally important, the simplest approaches to discovering and extracting biographical information from text have not been implemented. Further, no standard evaluations have been developed for summarization in general, but an evaluation methodology for this research is described and performed.