Identifying destinations automatically from human generated route directions

Xiao Zhang*, Prasenjit Mitra, Alexander Klippel, Alan M. MacEachren

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

4 Citations (Scopus)

Abstract

Automatic and accurate extraction of destinations in human-generated route descriptions facilitates visualizing text route descriptions on digital maps. Such information further supports research aiming at understanding human cognition of geospatial information. However, as reproted in previous work, the recognition of destinations is not satisfactory. In this paper, we show our approach and achievements in improving the accuracy of destination name recognition. We identified and evaluated multiple features for classifying a named entity to be either "destination" or "non- destination"; after that, we use a simple yet effective post-processing algorithm to improve classification accuracy. Comprehensive experiments confirm the effectiveness of our approach.
Original languageEnglish
Title of host publication19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2011
Pages373-376
Number of pages4
DOIs
Publication statusPublished - Nov 2011
Externally publishedYes
Event19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2011 - Chicago, IL, United States
Duration: 1 Nov 20114 Nov 2011

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Conference/symposium

Conference/symposium19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2011
Country/TerritoryUnited States
CityChicago, IL
Period1/11/114/11/11

Keywords

  • destination name classification
  • driving directions
  • geospatial information extraction

Fingerprint

Dive into the research topics of 'Identifying destinations automatically from human generated route directions'. Together they form a unique fingerprint.

Cite this