The Relevance of Spatial Relation Terms and Geographical Feature Types

Spatial relation terms can generally indicate spatial relations described in natural language context. Their semantic representation is closely related to geographical entities and their characteristics e.g. geometry, scale and geographical feature types. This paper proposes a quantitative approach to explore the semantic relevance of spatial relation terms and geographical feature types of geographical entities in text. Firstly, a classification of spatial relation terms is performed. Secondly, the “Overlap” similarity measure is introduced to define the relevance of spatial relation terms and geographical feature types based on a large scale annotation corpus. Finally, a knowledge base based on protégé is developed to formally represent and visualize geographical feature types, spatial relation classifications, and the relevance of spatial relation terms and geographical feature types. This study indicates that spatial relation terms are strongly relevant to geographical feature types. The semantic representation of topological relation terms is diverse and their relevance with geographical feature types is much stronger than directional relation and distance relation terms, but the annotation quality and the classification granularity of geographical entities in the corpus have a great effect on the performance.