Using Semantic Networks for Geographic Information Retrieval

Leveling, Johannes; Hartrumpf, Sven; Veiel, Dirk

doi:10.1007/11878773_109

Cited by 8 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Candidate terms are searched in gazetteers or geographic databases, using string matching or special text elements such as capitalized words in sentences. Indirect references to places are called implicit geographic evidence (Cardoso et al, 2008) or location indicators (Leveling et al, 2006). They are urban addresses, references to related entities or landmarks, nicknames, or even sets of coordinates.…”

Section: Task 1: Geoparsingmentioning

confidence: 99%

A survey on the geographic scope of textual documents

Monteiro

Davis

Fonseca

2016

Computers & Geosciences

View full text Add to dashboard Cite

Section: Task 1: Geoparsingmentioning

confidence: 99%

A survey on the geographic scope of textual documents

Monteiro

Davis

Fonseca

2016

Computers & Geosciences

View full text Add to dashboard Cite

“…There are also ideas to use Wikipedia as Gazetteer [12,21]. Semantic networks [14] can be helpful to find implicit geographic references like ''Eiffel Tower'', which refers to Paris. Ambiguities are usually split in cases where geographic names are confused with non-geographic ones (geo/non-geoambiguities) and in cases where two geographic names are confused (geo/geoambiguities) [6].…”

Section: Related Workmentioning

confidence: 99%

Toward location-aware Web: extraction method, applications and evaluation

Hess

Magagna

Sutanto

2013

Pers Ubiquit Comput

View full text Add to dashboard Cite

Location-based services (LBS) belong to one of the most popular types of services today. However, a recurring issue is that most of the content in LBS has to be created from scratch and needs to be explicitly tagged to locations, which makes existing Web content not directly usable for LBS. In this paper, we aim at making Web sites location-aware and feed this information to LBS. Our approach toward location-aware Web is threefold: First, we present a location extraction method: SALT. It receives Web sites as input and equips them with location tags. Compared to other approaches, SALT is capable of extracting locations with a precision up to the street level. Performance evaluations further show high applicability for practice. Second, we present three applications for SALT: Webnear.me, Local Browsing and Local Facebook. Webnear.me offers location-aware Web surfing through a mobile Web site and a smartphone app. Local Browsing adds the feature to browse by nearby tags, extracted from Web sites delivered by SALT. Local Facebook extends location tagging to social networks, allowing to run SALT on one's own and one's friends' timeline. Finally, we evaluate SALT for technology acceptance of Webnear.me through a formative user study. Through real user data, collected during a 3 months pilot field deployment of Webnear.me, we assess whether SALT is a proper instance of ''location of a Web site''.

show abstract

“…Figure 1 shows an example query from the GeoCLEF test set; Figure 2 shows an excerpt from a sample document. As in a setup for previous GIR experiments on GeoCLEF data [12,13], the document representation were indexed with the Zebra database management system [6], which supports a standard relevance ranking (tf-idf IR model).…”

Section: Data Preprocessingmentioning

confidence: 99%

“…Location names are identified by a lookup in large name lists; see [12] for a more detailed description of document preprocessing. Mikheev et al [15] argue that named entity recognition works well without employing large resources of toponyms at all.…”

Section: Data Preprocessingmentioning

confidence: 99%

Exploring term selection for geographic blind feedback

Leveling

2007

Proceedings of the 4th ACM Workshop on Geographical Information Retrieval

Self Cite

View full text Add to dashboard Cite

Standard blind feedback techniques have been applied to geographic information retrieval (GIR) with limited success. To facilitate more geographically oriented blind feedback, this paper explores the use of meronymy (part-whole) relations for term selection, based on a meronymy predicate for selecting feedback terms. Different methods are evaluated on the German GeoCLEF 2006 data, measuring standard evaluation measures such as mean average precision (MAP) or precision at five documents. To achieve a trade-off between coverage and ambiguity, a new geographic knowledge base is created, containing important place names only, which reduces ambiguity.Results indicate that blind feedback improves performance for some topics, but does not considerably change MAP in the setup. However, a higher precision at five documents is achieved if more geographically oriented term selection criteria are applied.

show abstract

Using Semantic Networks for Geographic Information Retrieval

Cited by 8 publications

References 6 publications

A survey on the geographic scope of textual documents

A survey on the geographic scope of textual documents

Toward location-aware Web: extraction method, applications and evaluation

Exploring term selection for geographic blind feedback

Contact Info

Product

Resources

About