Geo-referencing with semi-automatic gazetteer expansion using lexico-syntactical patterns and co-reference analysis

Geo-referencing is a key task for geographical information retrieval because it allows unstructured or textual documents (i.e., Web pages) to be associated with geographical locations, which are then used by geo-search engines to index documents and search information by spatial criteria. This work proposes a strategy to extract geo-references from textual documents that combine natural language-processing techniques and co-reference solving heuristics, which in turn can be used to expand a geographical gazetteer. Implicit geographical entities (i.e., those entities referred to by pronouns) are recognized and incorporated into the gazetteer that is updated and used for georeferencing tasks. Experiments show the promise of the approach to geo-referencing Web pages when dealing with implicit and/or indirect geo-references.