Skip to Main Content
A hybrid information extraction (IE) framework based on geographical term detection approach has been developed to extract geographical information from an unrestricted Hindi text. The relationship between geographical entities extracted with the adjacent text is shown graphically so that information about these entities can be related. The system, a combination of statistically and linguistically motivated techniques, identifies single geographical names and multiple geographical names as well. The method is applied on Hindi language text, but the approach can be adapted for other languages also. The paper presents some experiments illustrating the accuracy of the method. The system being developed is in a prototype stage and will be extended to include relation mark-up as well.