Abstract
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.
- Frank, A. (2009): Why is scale an effective descriptor for data quality? The physical and ontological rationale for imprecision and level of detail. In: G. Navratil (ed.): Research Trends in Geographic Information Science. Berlin: Springer, p. 39--62.Google Scholar
- Gravano, L.; Hatzivassiloglou, V.; Lichtenstein, R. (2003): Categorizing web queries according to geographical locality. In: D. Kraft (ed.): CIKM-03 Proceedings of the 12th Int. Conference on Information and Knowledge Management. New York: ACM Press. Google ScholarDigital Library
- Girardin, F.; Blatt, J.; Calabrese, F.; Dal Fiore, F.; Ratti, C. (2008): Digital footprinting: Uncovering tourists with user-generated content. IEEE Pervasive Computing 7 (4), p. 36--43. Google ScholarDigital Library
- Girardin, F.; Vaccari, A.; Gerber, A.; Biderman, A.; Ratti, C. (2009): Quantifying urban attractiveness from the distribution and density of digital footprints. International Journal of Spatial Data Infrastructure Research 4, p. 175--200Google Scholar
- Helleland, B. (2006): The social and cultural values of geographic names. In: Manual for the National Standardization of Geographical Names. New York: United Nations Publication, S. 121--128. http://unstats.un.org/unsd/publication/seriesm/seriesm_88e.pdfGoogle Scholar
- Henrich, A.; Lüdecke, V. (2007): Characteristics of geographic information needs. In: R. Purves et al. (eds.): GIR-07 Proceedings of the 4th ACM Workshop On Geographic Information Retrieval, ACM Press, p. 1--6 Google ScholarDigital Library
- Henrich, A.; Lüdecke, V. (2009): Measuring similarity of geographic regions for geographic information retrieval. In: Boughanem, M. et al. (eds.): ECIR-09 Proceedings 31th European Conference on IR Research, Berlin: Springer (LNCS 5478), p. 781--785 Google ScholarDigital Library
- Leidner, J.; Sinclair, G.; Webber, B. (2003): Grounding spatial named entities for information extraction and question answering. In: A. et al Kornai (eds.): GEOREF '03 Proceedings Workshop on Analysis of Geographic References, ACL, p. 31--38. Google ScholarDigital Library
- Jones, C.; Purves, R.; Clough, P.; Joho, H. (2008): Modelling vague places with knowledge from the Web. International Journal of Geographical Information Science 22 (10), p. 1045--1065. Google ScholarDigital Library
- Montello, Daniel; Goodchild, Michael; Gottsegen, Jonathon; Fohl, Peter (2003): Where's downtown? Behavioral methods for determining referents of vague spatial queries. Spatial Cognition and Computation 3 (2&3), S. 185--204.Google ScholarCross Ref
- Schlieder C., Matyas C. (2009). Photographing a city: An analysis of place concepts based on spatial choices. Spatial Cognition and Computation 9 (3), p. 212--228Google ScholarCross Ref
- Schockaert, S. (2011). Vague regions in geographic information retrieval, SIGSPATIAL special issue on Geographic Information Retrieval, this issue Google ScholarDigital Library
- Smith, B.; Varzi, A. (2000): Fiat and bona fide boundaries. Philosophy and Phenomenological Research 60 (2), p. 401--420.Google ScholarCross Ref
- Straumann, R; Purves, R. (2008): Delineation of valleys and valley floors. In: T. Cova et al. (eds.): GIScience-08 Proceedings of the 5th Int. Conference on Geographic Information Science. Berlin: Springer (LNCS, 5266), p. 320--336. Google ScholarDigital Library
- Vögele, Thomas (2004): Spatial Information Retrieval with Place Names. Doctoral dissertation, University of Bremen. elib.suub.uni-bremen.de/publications/dissertations/E-Diss978_voegele.pdf.Google Scholar
Index Terms
- Spatial grounding with vague place models
Recommendations
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 1The task of named entity annotation of unseen text has recently been successfully automated with near-human performance.But the full task involves more than annotation, i.e. identifying the scope of each (continuous) text span and its class (such as ...
Grounding spatial relations in text-only language models
AbstractThis paper shows that text-only Language Models (LM) can learn to ground spatial relations like left of or below if they are provided with explicit location information of objects and they are properly trained to leverage those locations. We ...
Highlights- A novel textual representation for complex scenes based on location tokens.
- Location tokens allow Language Models to ground spatial relations between objects.
- Using an automatic synthetic dataset we train Language Models for ...
Fuzzy representation of vague spatial descriptions in real estate advertisements
LocalRec '22: Proceedings of the 6th ACM SIGSPATIAL International Workshop on Location-based Recommendations, Geosocial Networks and GeoadvertisingGeocoding a spatial description is challenging since vernacular place names and vague spatial expressions give uncertainty and ambiguity to the description. Usually, digital gazetteers are used to match geospatial objects to their boundaries. However, ...
Comments