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 language | English |
|---|---|
| Title of host publication | GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems |
| Pages | 373-376 |
| Number of pages | 4 |
| DOIs | |
| Publication status | Published - 2011 |
| Externally published | Yes |
| Event | 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2011 - Chicago, IL Duration: 1 Nov 2011 → 4 Nov 2011 |
Other
| Other | 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2011 |
|---|---|
| City | Chicago, IL |
| Period | 1/11/11 → 4/11/11 |
Fingerprint
Keywords
- destination name classification
- driving directions
- geospatial information extraction
ASJC Scopus subject areas
- Earth-Surface Processes
- Computer Science Applications
- Modelling and Simulation
- Computer Graphics and Computer-Aided Design
- Information Systems