Abstract

AbstractNatural language text which contains rich geographical knowledge is an important spatial information source for GIS. Automatic extraction of geographical attribute-values from unstructured text can not only enrich GIS information sources, but also enhance its expression capabilities and intelligibilities. Here a machine learning method was proposed to extract geographical attributes from text based on attribute keywords and rule database-driven. Firstly, based on bootstrapping method a geographical attribute dictionary was present, and geographical attribute syntactic rules were constructed from artificial induction. With the regular expression match, not only geographical attribute names and attribute values, but also the relevance of geographical entities and geographical attribute-values were extracted. Finally, with an experiment the commonly used geographical attribute names and the attribute-value extraction result are illustrated. The experiment results are able to achieve more than 85% precision and recall for geographical attribute names and values extraction, more than 75% precision and recall for the relevancy extraction.Keywordsgeographical attribute-valuessyntactic patternsbootstrapping methodGIS

Full Text

Published Version

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.