Logo des Repositoriums

Auflistung nach Schlagwort "Geographic information retrieval"

1 - 2 von 2
  • Zeitschriftenartikel
    Applying Geographic Information Retrieval
    (Datenbank-Spektrum: Vol. 14, No. 1, 2014) Ahlers, Dirk
    This article reports on the efforts to establish a research project on a geospatial search engine for the Latin American country of Honduras during the author’s research stay at a local university. Honduras is an interesting example of the challenges for information and knowledge management in developing countries as it combines many of the issues that are otherwise encountered more isolated or with less impact. These include low Web coverage in a low-resource country with limited Web infrastructure, and generally, work in challenging circumstances. The specific focus on geospatial information uncovers further issues that need to be addressed, such as informal addressing schemes or landmark-oriented location references, broad or incorrect locations for places, or insufficient ground truth in databases. While the tangible results of the project stay behind the original goals, several interesting results were achieved, which are condensed here as an experience report.
  • Zeitschriftenartikel
    Automated Interpretation of Place Descriptions: Determining Entity Types for Querying OSM
    (KI - Künstliche Intelligenz: Vol. 37, No. 1, 2023) Yousaf, Madiha; Schwartz, Tobias; Wolter, Diedrich
    This paper is concerned with interpretation of natural language place descriptions, as they are a rich source of geographic information. A place description is interpreted by matching geographic entities occurring in the text against the OpenStreetMap (OSM) database. This paper is mainly concerned with interpretation of paraphrased places, i.e., entities for which no name is given and which may only by described. Our objective is to determine suitable entity types that allow querying the OpenStreetMap database for the respective place. For example, if we wish to identify a place to eat , we have to check for entities of an a-priori unknown type (cafe, restaurant, etc.). Challenges arise from the open-endedness of language, its ambiguity, and context-sensitivity as well as from mismatches between human conceptualization of place and database ontologies. The contributions of this paper are, first, to present a hard problem that is key to geo-information retrieval beyond named entities. Second, we propose context-sensitive methods for identifying place types based on semantic word similarity. We evaluate the methods on text extracted from Wikipedia and travel blogs, revealing their contribution to advancing automated interpretation of place descriptions to paraphrased places.