TY  - CONF
AU  - Garbin, Eric
AU  - Mani, Inderjeet
A2  - 
T1  - Disambiguating toponyms in news
T2  - Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
PB  - Association for Computational Linguistics
C1  - Stroudsburg, PA, USA
PY  - 2005/
CY  -  
VL  - 
IS  - 
SP  - 363
EP  - 370
UR  - http://dx.doi.org/10.3115/1220575.1220621
DO  - 10.3115/1220575.1220621
KW  - geo
KW  - toponym
KW  - news
KW  - disambiguation
KW  - map
KW  - extraction
L1  - 
SN  - 
N1  - 
N1  - 
AB  - 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.
ER  -