Resolving spatial references using crowdsourced geographical data
2015 (English)In: Proceedings of the 20th Nordic Conference of Computational Linguistics, NODALIDA 2015, Linköping University Electronic Press, 2015, 61-68 p.Conference paper (Refereed)
We present a study in which we seek to interpret spatial references that are part of in-situ route descriptions. Our aim is to resolve these references to actual entities and places in the city using a crowdsourced geographic database (OpenStreetMap). We discuss the problems related to this task, and present a possible automatic reference resolution method that can find the correct referent in 68% of the cases using features that are easily computable from the map.
Place, publisher, year, edition, pages
Linköping University Electronic Press, 2015. 61-68 p.
Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-165612OAI: oai:DiVA.org:kth-165612DiVA: diva2:808672
20th Nordic Conference on Computational Linguistics, Wilna, Lithuania, 2015
FunderSwedish Research Council, 2013-4854
QC 201505082015-04-292015-04-292015-05-08Bibliographically approved