Information extraction from Arabic law documents

Abstract

Information hidden in unstructured or semi-structured documents can be quite useful. To pull this information, an information extraction system is needed. Making extracted information available in structured format enables answering more complex queries of interest to law professionals. In this paper we address the issue of Arabic information extraction from law documents. We describe a system that extracts some important information of interest to potential users of these documents with minimal human intervention. The system employs a hybrid approach that utilizes machine learning and rule based approaches to extract the needed information from the texts.