This project is focused on toponym disambiguation and geographical focus identification in text. The goal is to improve the performance of geographic information retrieval systems. This paper describes the problems faced, working hypothesis, tasks proposed and goals currently achieved.

Toponym resolvers identify the specific locations referred to by ambiguous placenames in text. Most resolvers are based on heuristics using spatial relationships between multiple toponyms in a document, or metadata such as population. This paper shows that text-driven disambiguation for toponyms is far more effective. We exploit document-level geotags to indirectly generate training instances f...

One of the potentially most relevant pieces of metadata for filtering studies in environmental science is the geographic region in which the study took place (the “study region”). In this paper, we apply support vector machines to the automatic classification of study region in a dataset of titles and abstracts from environmental science literature, using features including frequency distributi...

Toponym extraction and disambiguation have received much attention in recent years. Typical fields addressing these topics are information retrieval, natural language processing, and semantic web. This paper addresses two problems with toponym extraction and disambiguation. First, almost no existing works examine the extraction and disambiguation interdependency. Second, existing disambiguation...

Toponym resolution, or grounding names of places to their actual locations, is an important problem in analysis of both historical corpora and present-day news and web content. Recent approaches have shifted from rule-based spatial minimization methods to machine learned classifiers that use features of the text surrounding a toponym. Such methods have been shown to be highly effective, but the...

Nowadays, spatial analysis in text is widely considered as important for both researchers and users. In certain fields such as epidemiology, the extraction of spatial information in text is crucial and both resources and methods are necessary. In most of spatial analysis process, gazetteer is a commonly used resource. A gazetteer is a data source where toponyms (place name) are associated with ...

We present minimally supervised methods for training and testing geographic name disambiguation (GND) systems. We train data-driven place name classifiers using toponyms already disambiguated in the training text — by such existing cues as “Nashville, Tenn.” or “Springfield, MA” — and test the system on texts where these cues have been stripped out and on hand-tagged historical texts. We experi...

A key problem that arises when unstructured text is being queried is that of properly recognizing and exploiting geographical terms and entities. Here we describe a mechanism for probabilistic toponym resolution, and our experiments with the new method in the setting of the 2005 GeoCLEF queries and judgments. The new method gives improved retrieval effectiveness on a subset of the topics.