Ontology and NLP support for building disaster knowledge base

The data from pre, post and during disasters play a very important and vital role while immediate decision making in emergency management. Data availability, analysis, and exchange build up a critical knowledge base that helps in taking the right decision at the right time. Voluminous data is available through various sources in heterogeneous formats. It is a very big challenge for utilization of such massive heterogeneous data in disaster management situations. Disaster data is widely available in various documents and formats. Past disasters, anticipated disasters and during the disasters, a large amount of data is getting exchanged in various documents between different agencies. Effective techniques to extract and gather the data from heterogeneous documents helps in right data extraction and build up a knowledge base to formulate ease of analysis and modeling. Ontology based semantic technology is a powerful mechanism that supports information integration, exchange, share, reuse and build a knowledge base from heterogeneous information sources. The current research work focuses on three aspects of knowledge base system for effective disaster management. The current research work implemented a mechanism to extract relevant information from semi-structured and structured heterogeneous documents using NLP, representing extracted information in homogeneous and machine understandable format using RDF and map the RDF triples to appropriate concepts of the disaster management domain ontologies. This is very novel and effective means of data usage mechanism to help and guide policy makers, disaster mitigation agencies and society at large.