This paper is involved with extracting spatial information from text. We seek to geo-reference all spatial entities mentioned in a piece of text. The focus of this paper is to investigate the contribution of spatial and ontological reasoning to spatial interpretation of text. A preliminary study considering descriptions of cities and geographical regions from English Wikipedia suggests that spatial and ontological reasoning can be more effective to resolve ambiguities in text than a classical text understanding pipeline relying on parsing.
@InProceedings{yousaf_et_al:LIPIcs.GISCIENCE.2018.71, author = {Yousaf, Madiha and Wolter, Diedrich}, title = {{Spatial Information Extraction from Text Using Spatio-Ontological Reasoning}}, booktitle = {10th International Conference on Geographic Information Science (GIScience 2018)}, pages = {71:1--71:6}, series = {Leibniz International Proceedings in Informatics (LIPIcs)}, ISBN = {978-3-95977-083-5}, ISSN = {1868-8969}, year = {2018}, volume = {114}, editor = {Winter, Stephan and Griffin, Amy and Sester, Monika}, publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik}, address = {Dagstuhl, Germany}, URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GISCIENCE.2018.71}, URN = {urn:nbn:de:0030-drops-93997}, doi = {10.4230/LIPIcs.GISCIENCE.2018.71}, annote = {Keywords: spatial information extraction, geo-referencing, spatial reasoning} }
Feedback for Dagstuhl Publishing