@InProceedings{alolimat-EtAl:2018:C18-12,
  author    = {Al-Olimat, Hussein  and  Thirunarayan, Krishnaprasad  and  Shalin, Valerie  and  Sheth, Amit},
  title     = {Location Name Extraction from Targeted Text Streams using Gazetteer-based Statistical Language Models},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  month     = {August},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {1986--1997},
  abstract  = {Extracting location names from informal and unstructured social media data requires the identification of referent boundaries and partitioning compound names. Variability, particularly systematic variability in location names (Carroll, 1983), challenges the identification task. Some of this variability can be anticipated as operations within a statistical language model, in this case drawn from gazetteers such as OpenStreetMap (OSM), Geonames, and DBpedia. This permits evaluation of an observed n-gram in Twitter targeted text as a legitimate location name variant from the same location-context. Using n-gram statistics and location-related dictionaries, our Location Name Extraction tool (LNEx) handles abbreviations and automatically filters and augments the location names in gazetteers (handling name contractions and auxiliary contents) to help detect the boundaries of multi-word location names and thereby delimit them in texts.},
  url       = {http://www.aclweb.org/anthology/C18-1169}
}