Georeferenced data sets are often large and complex. Natural Language Generation (NLG) systems are beginning to emerge that generate texts from such data. One of the challenges these systems face is the gener- ation of geographic descriptions referring to the location of events or patterns in the data. Based on our studies in the domain of me- teorology we present a two staged approach to generating geographic descriptions. The first stage involves using domain knowledge based on the task context to select a frame of reference, and the second involves using constraints imposed by the end user to select values within a frame of reference. Because geographic concepts are inherently vague our approach does not guarantee a distinguish- ing description. Our evaluation studies show that NLG systems, because they can analyse input data exhaustively, can produce more fine-grained geographic descriptions that are more useful to end users than those generated by human experts.
|Title of host publication||Proceedings of 12th European Workshop on Natural Language Generation (ENLG2009)|
|Place of Publication||Athens, Greece|
|Publisher||Association for Computational Linguistics|
|Number of pages||8|
|Publication status||Published - Mar 2009|
Turner, R., Sripada, Y., & Reiter, E. (2009). Generating Approximate Geographic Descriptions. In Proceedings of 12th European Workshop on Natural Language Generation (ENLG2009) (pp. 42-49). Association for Computational Linguistics. http://www.aclweb.org/anthology-new/W/W09/W09-0607.pdf