1. Traditionally, geographic information used in spatial analysis and research was almost exclusively produced by a relatively small set of governmental and commercial actors, and took the form of ...

Natural language location descriptions frequently describe object locations relative to other objects (the house near the river). Geospatial prepositions (e.g.near) are a key element of these descriptions, and the distances associated with proximity, adjacency and topological prepositions are thought to depend on the context of a specific scene. When referring to the context, we include consideration of properties of the relatum such as its feature type, size and associated image schema. In this paper, we extract spatial descriptions from the Google search engine for nine prepositions across three locations, compare their acceptance thresholds (the distances at which different prepositions are acceptable), and study variations in different contexts using cumulative graphs and scatter plots. Our results show that adjacency prepositions next to and adjacent to are used for a large range of distances, in contrast to beside; and that topological prepositions in, at and on can all be used to indicate proximity as well as containment and collocation. We also found that reference object image schema influences the selection of geospatial prepositions such as near and in.

A considerable proportion of records that describe biological specimens (flora, soil, invertebrates), and especially those that were collected decades ago, are not attached to corresponding geographical coordinates, but rather have their location described only through textual descriptions (e.g. North Canterbury, Selwyn River near bridge on Springston-Leeston Rd). Without geographical coordinates, millions of records stored in museum collections around the world cannot be mapped. We present a method for predicting the distance and direction associated with human language location descriptions which focuses on the interpretation of geospatial prepositions and the way in which they modify the location represented by an associated reference place name (e.g. near the Manawatu River). We study eight distance-oriented prepositions and eight direction-oriented prepositions and use machine learning regression to predict distance or direction, relative to the reference place name, from a collection of training data. The results show that, compared with a simple baseline, our model improved distance predictions by up to 60% and direction predictions by up to 31%.

References to geographic locations are common in text data sources including social media and web pages. They take different forms from simple place names to relative expressions that describe location through a spatial relationship to a reference object (e.g. the house beside the Waikato River). Often complex, multi-word phrases are employed (e.g. the road and railway cross at right angles; the road in line with the canal) where spatial relationships are communicated with various parts of speech including prepositions, verbs, adverbs and adjectives. We address the problem of automatically detecting relative geospatial location descriptions, which we define as those that include spatial relation terms referencing geographic objects, and distinguishing them from non-geographical descriptions of location (e.g. the book on the table). We experiment with several methods for automated classification of text expressions, using features for machine learning that include bag of words that detect distinctive words, word embeddings that encode meanings of words and manually identified language patterns that characterise geospatial expressions. Using three data sets created for this study, we find that ensemble and meta-classifier approaches, that variously combine predictions from several other classifiers with data features, provide the best F-measure of 0.90 for detecting geospatial expressions.

The way people describe where things are is one of the central questions of spatial information theory and has been the subject of considerable research. We investigate one particular type of location description, fictive motion (as in, The range runs along the coast). The use of this structure is known to highlight particular properties of the described entity, as well as to convey its configuration in physical space in an effective way. We annotated 496 fictive motion structures in seven corpora that represent different types of spatial discourse – news, travel blogs, texts describing outdoor pursuits and local history, as well as image and location descriptions. We analysed the results not only by examining the distribution of fictive motion structures across corpora, but also by exploring and comparing the semantic categories of verbs used in fictive motion. Our findings, first, add to our knowledge of location description strategies that go beyond prototypical locative phrases. They further reveal how the use of fictive motion varies across types of spatial discourse and reflects the nature of the described environment. Methodologically, we highlight the benefits of a cross-corpora analysis in the study of spatial language use across a variety of contexts.

There is increasing interest in detecting the presence of geospatial locative expressions that include spatial relation terms such as near or within . Being able to do so provides a foundation for interpreting relative descriptions of location and for building corpora that facilitate the development of methods for spatial relation extraction and interpretation. Here we evaluate the use of a spatial role labelling procedure to distinguish geospatial uses of prepositions from other spatial and non-spatial uses and experiment with the use of additional machine learning features to improve the quality of detection of geospatial prepositions. An annotated corpus of nearly 2000 instances of preposition usage was created for training and testing the classifiers.

Natural language descriptions of location can be complex, involving many different elements and often describing location by reference to other objects. Descriptions may be vague, and their meaning often depends upon the context within which the description has been expressed. Many previous approaches use mathematical models, focus on prepositions, and have had limited success and application. We present an approach to the interpretation of geospatial natural language expressions that uses a knowledge base of expressions for which human interpretations (in the form of degree of match to one of 50 geometric configurations) are known. Our approach interprets new expressions by finding the most similar knowledge base expression and adopting its meaning. We determine expression similarity using four different methods: element match; linguistic collocation approaches (Cosine); wordnet semantic network distance and a new approach that incorporates the contextual aspects of the expression including scale, geometry type, axial structure, image-schema and liquid/solid. As well as preposition, relatum and locatum, we consider spatial adjectives, adverbs, verb and sub-parts of the relatum and locatum. The method that incorporates context was the most successful of the four tested, selecting the same geometric configuration as human respondents in 69% of cases.

This paper has presented the use of NSM combined with feature type ontologies to describe the behavior of geospatial features, and explained how such descriptions can be used to match user queries against queries that can be executed on a database, allowing users to express their queries in behavioral terms, using restricted natural language. A similar approach may be applied to the behavioral semantics of geographic feature types in ontologies or web services.

The use of a semantically rich registry containing a Feature Type Catalogue (FTC) to represent the semantics of geographic feature types including operations, attributes and relationships between feature types is required to realise the benefits of Spatial Data Infrastructures (SDIs). Specifically, such information provides a more complete representation of the semantics of the concepts used in the SDI, and enables advanced navigation, discovery and utilisation of discovered resources. The presented approach creates an FTC implementation in which attributes, associations and operations for a given feature type are encapsulated within the FTC, and these conceptual representations are separated from the implementation aspects of the web services that may realise the operations in the FTC. This differs from previous approaches that combine the implementation and conceptual aspects of behaviour in a web service ontology, but separate the behavioural aspects from the static aspects of the semantics of the concept or feature type. These principles are demonstrated by the implementation of such a registry using open standards. The ebXML Registry Information Model (ebRIM) was used to incorporate the FTC described in ISO 19110 by extending the Open Geospatial Consortium ebRIM Profile for the Web Catalogue Service (CSW) and adding a number of stored queries to allow the FTC component of the standards‐compliant registry to be interrogated. The registry was populated with feature types from the marine domain, incorporating objects that conform to both the object and field views of the world. The implemented registry demonstrates the benefits of inheritance of feature type operations, attributes and associations, the ability to navigate around the FTC and the advantages of separating the conceptual from the implementation aspects of the FTC. Further work is required to formalise the model and include axioms to allow enhanced semantic expressiveness and the development of reasoning capabilities.

The COastal and Marine Perception Application for Scientific Scholarship (COMPASS) is a knowledge infrastructure that supports enhanced discovery of scientific resources, including publications, data sets and web services. It provides users with the ability to discover resources on the basis of domain knowledge using ontologies, and scientific knowledge, including the scientific models, theories and methods that were used to conduct the research described by the resource. The application includes an architecture that adopts standards from the geospatial information community to ensure interoperability between repositories and allow interaction with content from digital libraries. The architecture shows how ontologies can be used as a registry for an interoperable infrastructure. A prototype was successfully implemented and evaluated with users, finding enthusiasm and support for the approach, with some suggestions for improvements of the prototype implementation.