Challenges in anaphora resolution in the news media genre
This paper discusses the characteristics of anaphora found in written News Media genre and describes an initial implementation of an algorithm to resolve the anaphors. The paper forms part of wider research aimed at using resolved anaphors for text visualization. The algorithm described is light weight and incremental, in that, it builds vocabulary as it processes documents to be used in future. The input data is also tested on two publicly available anaphora resolution algorithms and the results compared to the algorithm described in this paper. Finally it discusses the challenges in developing light weight algorithms to resolve anaphors in the News Media genre and further research to overcome some of these challenges.