Semantic place localization from narratives

摘要: Place narratives provide a rich resource of learning how humans localize places. localization can be done in various ways, relative to other spatial referents, and agents their activities which these referents may involved. How we describe places based on semantic relationships objects, qualities, activities? relations help us improve automated implicit textual descriptions? In this paper, motivate research extraction place statements from text corpora used for improving document retrieval reconstructing locations. The idea is combine Semantic Web reasoning with existing geographic information (GIR) structural purpose. GIR technology have matured during the last years, but still largely exist parallel. Current approaches been focusing unstructured word lists texts, including toponyms features, not human descriptions sentence level.