Categorizing web queries according to geographical locality
CIKM '03 Proceedings of the twelfth international conference on Information and knowledge management
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
Characteristics of geographic information needs
Proceedings of the 4th ACM workshop on Geographical information retrieval
Delineation of Valleys and Valley Floors
GIScience '08 Proceedings of the 5th international conference on Geographic Information Science
Modelling vague places with knowledge from the Web
International Journal of Geographical Information Science - Digital Gazetteer Research
Digital Footprinting: Uncovering Tourists with User-Generated Content
IEEE Pervasive Computing
Measuring Similarity of Geographic Regions for Geographic Information Retrieval
ECIR '09 Proceedings of the 31th European Conference on IR Research on Advances in Information Retrieval
Vague regions in Geographic Information Retrieval
SIGSPATIAL Special
Hi-index | 0.00 |
Vagueness arises as a problem in the context of grounding named entities, a central task in geographic information retrieval (GIR) which consists in establishing the entities' "denotation with respect to the world or a model" [8]. We use the term spatial grounding in a slightly more general sense to refer to the association of any type of spatial descriptor with a place model. In the simplest case, the descriptor consists of a toponym and the place model is provided by a (vague) geographic region. More complex descriptors make use of prepositional phrases or even a text span comprising many sentences, e.g. a travel blog entry. However, descriptors are in no way limited to natural language expressions. A frequently used descriptor in mobile GIR is the geographic position of the user as part of the specification of an information need. Furthermore, spatial activities such as taking photographs can also act as descriptors for places models ("tell me more about the focused object"). Different place models for representing the vagueness of regions have been proposed including supervaluation semantics and qualitatively augmented fuzzy footprints [12]. In this paper we concentrate on approaches to grounding that exploit diverse information sources, for instance, topographic data or the spatial behavior of a user community, to determine place models which are sometimes more complex than point sets.