@inproceedings{garbin2005disambiguating,
  abstract = {This research is aimed at the problem of disambiguating toponyms (place names) in terms of a classification derived by merging information from two publicly available gazetteers. To establish the difficulty of the problem, we measured the degree of ambiguity, with respect to a gazetteer, for toponyms in news. We found that 67.82% of the toponyms found in a corpus that were ambiguous in a gazetteer lacked a local discriminator in the text. Given the scarcity of human-annotated data, our method used unsupervised machine learning to develop disambiguation rules. Toponyms were automatically tagged with information about them found in a gazetteer. A toponym that was ambiguous in the gazetteer was automatically disambiguated based on preference heuristics. This automatically tagged data was used to train a machine learner, which disambiguated toponyms in a human-annotated news corpus at 78.5% accuracy.},
  acmid = {1220621},
  address = {Stroudsburg, PA, USA},
  author = {Garbin, Eric and Mani, Inderjeet},
  booktitle = {Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing},
  doi = {10.3115/1220575.1220621},
  interhash = {566910cb6e9745ee70da19d2ccafaffa},
  intrahash = {de574cf3bff3a3748fcd9bd5a9a0f3d1},
  location = {Vancouver, British Columbia, Canada},
  numpages = {8},
  pages = {363--370},
  publisher = {Association for Computational Linguistics},
  title = {Disambiguating toponyms in news},
  url = {http://dx.doi.org/10.3115/1220575.1220621},
  year = 2005
}