Ontology-Based Information Extraction: Current Approaches

The purpose of Information Extraction (IE) is extracting information from unstructured, or semi structured machine readable documents by automatic means. Generally this means dealing with human language texts using natural language processing (NLP) techniques. Recently on the market of IE systems a new player emerged. Ontology-Based IE (OBIE) idea consequently gains more and more supporters. In this approach a crucial role in the IE process is played by ontology (formal representation of the knowledge by a set of concepts within a domain and the relationships between those concepts). Using Ontology as one of the IE tools makes OBIE very convenient approach for gathering information that can be later on used in construction of Semantic Web. In this paper I will explain the idea of OBIE with its fl aws and advantages. I will try not only to provide theoretical approach, but also to review current trends in this fi eld. This will be done to point out some common architecture in currently used systems and in the end classify them based on diff erent factors depending on their usability in real life application. As a conclusion an attempt to identify possible trends and directions in this fi eld will be made.