Modern Information Retrieval
Computing Geographical Scopes of Web Resources
VLDB '00 Proceedings of the 26th International Conference on Very Large Data Bases
Geographical Information Retrieval with Ontologies of Place
COSIT 2001 Proceedings of the International Conference on Spatial Information Theory: Foundations of Geographic Information Science
Web-a-where: geotagging web content
Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Detecting dominant locations from search queries
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Extracting metadata for spatially-aware information retrieval on the internet
Proceedings of the 2005 workshop on Geographic information retrieval
Grounding spatial named entities for information extraction and question answering
HLT-NAACL-GEOREF '03 Proceedings of the HLT-NAACL 2003 workshop on Analysis of geographic references - Volume 1
A confidence-based framework for disambiguating geographic terms
HLT-NAACL-GEOREF '03 Proceedings of the HLT-NAACL 2003 workshop on Analysis of geographic references - Volume 1
Disambiguating toponyms in news
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
STEWARD: architecture of a spatio-textual search engine
Proceedings of the 15th annual ACM international symposium on Advances in geographic information systems
A conceptual density-based approach for the disambiguation of toponyms
International Journal of Geographical Information Science
Proceedings of the 16th ACM SIGSPATIAL international conference on Advances in geographic information systems
An efficient location extraction algorithm by leveraging web contextual information
Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems
Landmark extraction: a web mining approach
COSIT'05 Proceedings of the 2005 international conference on Spatial Information Theory
Corpus-based place metadatabase generation for geocoding
Proceedings of the 27th Annual ACM Symposium on Applied Computing
Hi-index | 0.00 |
Importance of geocoding is emphasized in order to develop location-aware information retrieval systems for documents which include place names. Geocoding is used for translating those place names to geocodes. A geocode is often a pair of latitude and longitude values. In prior work, the first vertical geo/geo disambiguation method was developed for the documents. This disambiguation allows in finding fine-grained places that are relevant to ambiguous place names. However, the names of the fine-grained places have not yet appeared in the documents. A main feature of the prior method was based on a hypothesis that places would be identified by geographical and nongeographical features of themselves. Geographical features of each place are defined as the descriptions for identifying it, such as its geocode, its full address string, and its names. Nongeographical features of each place describe the location-independent aspects of historical events and objects that appeared there. Using conventional information retrieval techniques, the prior method was implemented for using only the statistics of terms that were included in both features of places. However, this implementation ignored geographical features of places in geocoding. This paper presents a new implementation method for improving the prior method. A main feature of the proposed method is to extend the prior method by a new parameter. This parameter is used for emphasizing geographical features of all places in geocoding. Through several experiments, the accuracy of the proposed method reached up to around 90% when geographical features of places were emphasized in a geocoding process.