Title: Event extraction from corefering mentions to enrich semantic web metadata

Authors: S. Sangeetha; Michael Arock

Addresses: Department of Computer Applications, National Institute of Technology, Tiruchirapalli-620015, Tamilnadu, India ' Department of Computer Applications, National Institute of Technology, Tiruchirapalli-620015, Tamilnadu, India

Abstract: Since an enormous amount of information is available on the web and much time is needed to find and read the desired information, users require precise information from the documents. More specifically, most users are interested in precise information about events occurring in different parts of the world, such as when and where the event has occurred and who was involved in the event. The task of finding such information is called event extraction. Event extraction from text documents is an important task in the field of natural language processing, as it helps improve information retrieval and summarisation, as well as enriching the semantic web with event-based metadata. This paper provides a method to extract event arguments from corefering sentences of a particular event instance using rule learning based on rough sets. It also provides a metadata adoption strategy to exploit the results in the semantic web environment as metadata.

Keywords: event extraction; ACE event; event characterisation; corefering mentions; semantic web metadata; text documents; natural language processing; NLP; information retrieval; summarisation; corefering sentences; rule learning; rough sets; coreference.

DOI: 10.1504/IJAIP.2014.062172

International Journal of Advanced Intelligence Paradigms, 2014 Vol.6 No.2, pp.95 - 112

Received: 09 Aug 2013
Accepted: 02 Dec 2013
Published online: 28 Jun 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article