! -- Paper: 17 -->
|Event extraction is one of the challenges to be tackled in order to extract valuable insight from unstructured text. The process of automatically identifying events in a corpus of text and extracting comprehensive information about them is called event extraction. Although a number of systems have been proposed for event extraction, there is currently no publicly available system specific to management changes. This paper presents a novel event extraction system - AutoMC - that identifies management change events from business news articles. Specifically, we propose a novel regular expressions based management change event extraction algorithm. The effectiveness of AutoMC is validated empirically over generated data sets. The experimental results show that our system performs competitively in comparison to management change event detection studies in the literature. High event detection performance (78.72% accuracy score) is achieved by the proposed event extraction rule learning method.|
*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.