Detecting geospatial location descriptions in natural language text

Stock, Kristin; Jones, Christopher B.; Russell, Shaun; Radke, Mansi A.; Das, Parichay K.; Aflaki, Niloofar

doi:10.1080/13658816.2021.1987441

Cited by 16 publications

(17 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work focuses on the particular case of detection of geo-spatial prepositions within sentences that could contain multiple prepositions with different senses (of either geo-spatial, other-spatial, or non-spatial). For this more specialized task, we demonstrate that our best methods, which use deep learning, can achieve an F1 value of 0.94 (and precision of 0.96) which is a considerable improvement over the F1 value of 0.90 (precision 0.91) that was achieved in the classifier presented in Stock et al (2022). It may also be noted that the expressions classified in the latter work might not contain any geo-spatial preposition as the spatial relations could be communicated with other parts of speech.…”

Section: Related Workmentioning

confidence: 85%

“…Following Stock et al (2022)'s definition of geo‐spatial expressions, we define geo‐spatial prepositions in terms of both the preposition and the reference object. For a preposition to be geo‐spatial, it must meet two criteria.…”

Section: Methodsmentioning

confidence: 99%

“…However, there are cases in which such terms are used more generically, and in those cases might not be considered geo-spatial. Stock et al (2022) provide a detailed discussion of the challenges of classifying spatial language, providing an extensive explanation of borderline examples and specific types of challenges such as descriptions of weather and hypothetical or metonymic references. We also discuss some other borderline cases when we describe the annotation process in Section 4.1.2.…”

Section: Definition Of Geo-spatial Other-spatial and Non-spatial Prep...mentioning

confidence: 99%

“…As noted above, preposition sense detection by itself can be regarded as a sub‐task of relation extraction and can be treated as part of a relation extraction pipeline or integrated with the detection of located and reference objects. We regard the presentation of effective methods for preposition sense detection in isolation as being of value in that they have the potential to be integrated with geo‐spatial relation extraction methods, but they also serve the purpose of helping to identify the presence of sentences that are communicating geo‐spatial information (Stock et al, 2022). They can therefore serve as a filter prior to application of methods that extract entire spatial relations.…”

Section: Introductionmentioning

confidence: 99%

“…We regard the presentation of effective methods for preposition sense detection in isolation as being of value in that they have the potential to be integrated with geo-spatial relation extraction methods, but they also serve the purpose of helping to identify the presence of sentences that are communicating geo-spatial information (Stock et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Disambiguating spatial prepositions: The case of geo‐spatial sense detection

Radke

Gupta

Stock

et al. 2022

Transactions in GIS

Self Cite

View full text Add to dashboard Cite

Spatial relations in natural language are frequently expressed through prepositions. Thus, in the locative expressions “New York in the United States” and “the house on the river” the prepositions “in” and “on,” respectively, serve to communicate the relationships in space between the subject and object of the preposition. Automatic detection of the use of prepositions in a spatial and in particular a geo‐spatial sense that refers to geographic context is of interest in supporting automated methods for determining the actual geographic location referred to by locative expressions. This work focuses on disambiguation of prepositions in natural language, with the goal of distinguishing whether a preposition is used in a specifically geo‐spatial sense. We conduct machine learning experiments that demonstrate the clear benefit for geo‐spatial sense detection of using transformer model deep learning methods when compared with a variety of methods, that include Naive Bayes, support vector machine, and random forest classifiers with handcrafted linguistic features, and a bag of words approach with a meta‐classifier that adds geo‐spatial features. The best performance was obtained with the Bidirectional Encoder Representation from Transformer‐based XLNet transformer model, with a best precision of 0.96 and an F1 score of 0.94 when evaluated on a corpus of natural language expressions that were annotated for this task. We also conducted experiments to detect generic spatial sense, in which the best F1 score, of 0.95, was again obtained with XLNet.

show abstract

Section: Related Workmentioning

confidence: 85%

Section: Methodsmentioning

confidence: 99%

Section: Definition Of Geo-spatial Other-spatial and Non-spatial Prep...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Disambiguating spatial prepositions: The case of geo‐spatial sense detection

Radke

Gupta

Stock

et al. 2022

Transactions in GIS

Self Cite

View full text Add to dashboard Cite

show abstract

Pragmatic GeoAI: Geographic Information as Externalized Practice

Scheider

Richter

2023

Künstl Intell

View full text Add to dashboard Cite

Current artificial intelligence (AI) approaches to handle geographic information (GI) reveal a fatal blindness for the information practices of exactly those sciences whose methodological agendas are taken over with earth-shattering speed. At the same time, there is an apparent inability to remove the human from the loop, despite repeated efforts. Even though there is no question that deep learning has a large potential, for example, for automating classification methods in remote sensing or geocoding of text, current approaches to GeoAI frequently fail to deal with the pragmatic basis of spatial information, including the various practices of data generation, conceptualization and use according to some purpose. We argue that this failure is a direct consequence of a predominance of structuralist ideas about information. Structuralism is inherently blind for purposes of any spatial representation, and therefore fails to account for the intelligence required to deal with geographic information. A pragmatic turn in GeoAI is required to overcome this problem.

show abstract

Current topics and challenges in geoAI

Richter

Scheider

2023

Künstl Intell

View full text Add to dashboard Cite

Taken literally, geoAI is the use of Artificial Intelligence methods and techniques in solving geo-spatial problems. Similar to AI more generally, geoAI has seen an influx of new (big) data sources and advanced machine learning techniques, but also a shift in the kind of problems under investigation. In this article, we highlight some of these changes and identify current topics and challenges in geoAI.

show abstract

Detecting geospatial location descriptions in natural language text

Cited by 16 publications

References 42 publications

Disambiguating spatial prepositions: The case of geo‐spatial sense detection

Disambiguating spatial prepositions: The case of geo‐spatial sense detection

Pragmatic GeoAI: Geographic Information as Externalized Practice

Current topics and challenges in geoAI

Contact Info

Product

Resources

About