Ontology-based event modeling for semantic understanding of Chinese news story

Abstract

Describing and extracting event semantic information is essential to build an event knowledge base and applications in event and semantic level. However, most existing work deals with documents so they fail to provide sufficient semantic information about events in news articles. In this paper, considering W hat, W ho, W hen, W here, Why and H ow, the 5W1H elements of a piece of news, we propose a News Ontology Event Model (NOEM) which can describe 5W1H semantic elements of an event. The model defines concepts of entities (time, person, location, organization etc.), events and relationships to capture temporal, spatial, information, experiential, structural and causal aspect of events. A comparison to existing event models and an empirical case study show that NOEM can effectively model the semantic elements of news events and their relationship; and has a strong ability to represent knowledge facts and easily adapt to new domains. © 2012 Springer-Verlag.