Disambiguating Toponyms in News

@article{citeulike:940901, 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 unsuper- vised machine learning to develop disam- biguation 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.}, author = {Mani, Inderjeet and Garbin, Eric }, booktitle = {HLT '05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing}, citeulike-article-id = {940901}, doi = {10.3115/1220575.1220621}, keywords = {data-mining, disambiguation, geocoding, news}, pages = {363--370}, posted-at = {2008-05-11 20:40:09}, priority = {2}, title = {Disambiguating Toponyms in News}, url = {http://dx.doi.org/10.3115/1220575.1220621}, year = {2005} }

TY - JOUR ID - citeulike:940901 L3 - citeulike-article-id:940901 TI - Disambiguating Toponyms in News T2 - HLT '05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing SP - 363 EP - 370 N2 - 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 unsuper- vised machine learning to develop disam- biguation 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. KW - data-mining KW - disambiguation KW - geocoding KW - news AU - Mani, Inderjeet AU - Garbin, Eric PY - 2005/// UR - http://dx.doi.org/10.3115/1220575.1220621 ER -