Creating a Corpus of Geospatial Natural Language

Stock, Kristin; Pasley, Robert C.; Gardner, Zoe; Brindley, Paul; Morley, Jeremy; Cialone, Claudia

Abstract

The description of location using natural language is of interest for a number of research activities including the automated interpretation and generation of natural language to ease interaction with geographic information systems. For such activities, examples of geospatial natural language are usually collected from the personal knowledge of researchers, or in small scale collection activities specific to the project concerned. This paper describes the process used to develop a more generic corpus of geospatial natural language.

The paper discusses the development and evaluation of four methods for semi-automated harvesting of geospatial natural language clauses from text to create a corpus of geospatial natural language. The most successful method uses a set of geospatial syntactic templates that describe common patterns of grammatical geospatial word categories and provide a precision of 0.66. Particular challenges were posed by the range of English dialects included, as well as metaphoric and sporting references.

Citation

Stock, K., Pasley, R. C., Gardner, Z., Brindley, P., Morley, J., & Cialone, C. (2013). Creating a Corpus of Geospatial Natural Language. In T. Tenbrink, J. Stell, A. Galton, & Z. Wood (Eds.), Spatial Information Theory: 11th International Conference, COSIT 2013, Scarborough, UK, September 2-6, 2013. Proceedings (279-298). Springer. https://doi.org/10.1007/978-3-319-01790-7_16

• Publication Date: 2013
• Deposit Date: Dec 13, 2018
• Publisher: Springer
• Pages: 279-298
• Book Title: Spatial Information Theory: 11th International Conference, COSIT 2013, Scarborough, UK, September 2-6, 2013. Proceedings
• ISBN: 978-3-319-01789-1
• DOI: https://doi.org/10.1007/978-3-319-01790-7_16
• Public URL: https://nottingham-repository.worktribe.com/output/1410567
• Publisher URL: https://link.springer.com/chapter/10.1007/978-3-319-01790-7_16