Imene Bensalem*, Mohamed-Khireddine Kholladi*
* Faculty of Engineering Science
Computer Science department
Mentouri University, Constantine
MISC Laboratory, Algeria
Abstract
The way of referring to a place in the geographical space can be formal, based on the spatial coordinates, or informal, which we use in natural language by using toponyms (place names). A toponym can represent several geographical places. This ambiguity made problematic its conversion towards a unique formal representation. Toponym disambiguation in text is the task of assigning a unique location to an ambiguous place name in a given context. Several toponym disambiguation heuristics assume a geographical proximity between the toponyms of the same context. This proximity can be in term of spatial distance or in term of arborsecent relationship, i.e. proximity in the hierarchical tree of the world places. This paper presents a new toponym disambiguation heuristic in text based on the quantification of the arborescent proximity between toponyms. Our method was compared to the state of the art methods using GeoSemCor corpus, and it has outperformed them.
Keywords: Toponym Disambiguation, arborescent relationship, Geographical Density, referent hierarchical path