Extracting Multi Granular Implicit Spatial References in Event Descriptions

The information disseminated in this era comprise of explanation of concepts, description of products and narration of events which obviously has a geographic or spatial reference component present in it. The happening of an event is always tied up to a spatial location. Not only the description of events, but various scientific documents and historical documents are also replete with spatial descriptions in them. This logically leads to the conclusion by the previous studies that more than 80% of the searches are pertaining to geographic locations. Text documents imply the usage of natural language and as such it yields to explicit vague fuzzy descriptions involving linguistic terms such as near to, far from, to the east of, very close and also implicit vague spatial references. Any text document which contains physical location specifications such as place names, geographic coordinates, landmarks, country names etc., are supposed to contain the spatial information. The understanding and extraction of spatial components is a primal area of study not only in the field of information retrieval but also in various other fields such as Robotics, Psychology, Geosciences, Geography, Political Sciences, Geographic Economy, Environmental, Mining and Petroleum Engineering, Natural Resources, Epidemiology, Demography etc., Given a query involving events, the aim of this ongoing research work is to extract both the explicit and implicit spatial references from the text documents, exploiting the granularities. The input to the system would be a text Corpus and a Spatial Query event. The output of the system is the list of implicit and explicit spatial references associated with the event, showing the most possible, disambiguated location of the event queried.