How to identify appropriate key-value pairs for querying OSM

Representing and Reasoning with Context-Sensitive Vague Place Descriptions

“…This chapter is based on content from a published paper [404] in GIScience 2018 and [406] in GIR 2019. The chapter extends the query strategy discussions and how our system has been implemented using constrained specific queries.…”

“…In the case of spatial entities and concepts, such crisp classification may be hard to achieve, and concepts may vary across individuals. Instead, relations like 'near' may be more adequately represented using a semantic capturing vagueness, e.g., using Fuzzy [406] or probabilistic models [99]. Second, existing ontology languages do not support the spatial domain and manifold spatial relations to the extent required to empower spatial reasoning for computing likely interpretations of a locative phrase.…”

“…This research aims to develop an automated system capable of interpreting spatial language for dealing with place descriptions [406]. Effective automated interpretation is a combination of recognizing the geographic references and resolving them unambiguously to locations on the earth's surface [188] i.e., to relate all nouns in a sentence that represent geographic entities to corresponding entities in a geographic database( 1 [406], [99]. In order to map the entities the GIS should be able to ask questions like What is where?and should allow the users to query and extract information [99].…”

“…As language is rich and offers many words to communicate nuances of a single entity type and conceptualization of natural language entities in text and OSM often differ. Even the classification of a single entity type is subject to variations throughout the OSM database; thus, this task aims to identify similar OSM tags using semantic similarity for any word encountered [406].Last part of this section is mainly concerned with interpretation of paraphrased places, i.e., entities for which no name is given and which may only by described.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. Our objective is to determine suitable entity types that allow querying the Open Street Map database for the respective place.…”

“…Apply part-of-speech tagging to S Given a number of previously identified context words, this module is concerned with finding the semantically closest related OSM concepts in the form of key-value tags. Previous work often relies on WordNet [263] to establish semantic relationships [33,406]. We thus relate our approach to an approach using WordNet in order to identify its potential and possible weaknesses (Section 6.5.2.1).…”