,
Stephan Winter
,
Martin Tomko
Creative Commons Attribution 4.0 International license
A robust spatial annotation scheme that explicitly represents spatial elements and the links between them in English natural (human) language route descriptions is required to support computational interpretation. Yet, existing spatial annotation schemes for English do not capture all the spatial elements and links that occur in route descriptions, including perceptual expressions and reorientation actions. Using Formal Concept Analysis (FCA), the elements and links are derived by modeling the conceptual space of route descriptions. These elements and links are then compared against ISO-Space, an annotation standard for encoding spatial entities, motion events, and spatial relations [Pustejovsky et al., 2012], selected as the reference framework due to its relatively comprehensive coverage among existing schemes. Based on the analysis, targeted scheme refinements and extensions interoperable with ISO-Space are introduced. The resulting scheme is evaluated through two annotation rounds on 48 route descriptions drawn from four datasets. The results show improved consistency and increased annotation coverage through perceptual and reorientation links, which account for 23% of all annotated links, without compromising annotation reliability.
@InProceedings{goudarzialiakbari_et_al:LIPIcs.COSIT.2026.12,
author = {Goudarzi Ali Akbari, Samira and Winter, Stephan and Tomko, Martin},
title = {{Extending ISO-Space to Annotate Spatial Information in Route Descriptions}},
booktitle = {17th International Conference on Spatial Information Theory (COSIT 2026)},
pages = {12:1--12:23},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-438-3},
ISSN = {1868-8969},
year = {2026},
volume = {393},
editor = {Timpf, Sabine and Filomena, Gabriele and Kapaj, Armand and Zhu, Rui and Giudice, Nicholas A. and Manley, Ed},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2026.12},
URN = {urn:nbn:de:0030-drops-275560},
doi = {10.4230/LIPIcs.COSIT.2026.12},
annote = {Keywords: spatial language, spatial information annotation scheme, route description}
}