Browsing by Author "Jones CB"

Now showing 1 - 8 of 8
  • Thumbnail Image
    Item
    AI-based discovery of habitats from museum collections
    (Cell Press, 2024-04-02) Jones CB; Stock K; Perkins SE
    Museum collection records are a source of historic data for species occurrence, but little attention is paid to the associated descriptions of habitat at the sample locations. We propose that artificial intelligence methods have potential to use these descriptions for reconstructing past habitat, to address ecological and evolutionary questions.
  • Thumbnail Image
    Item
    Detecting geospatial location descriptions in natural language text
    (Taylor and Francis Group, 2022) Stock K; Jones CB; Russell S; Radke M; Das P; Aflaki N
    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.
  • Thumbnail Image
    Item
    Detecting the geospatialness of prepositions from natural language text
    (Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2019-09-01) Radke M; Das P; Stock K; Jones CB; Timpf S; Schlieder C; Kattenbeck M; Ludwig B; Stewart K
    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.
  • Thumbnail Image
    Item
    Large Multi-Modal Model Cartographic Map Comprehension for Textual Locality Georeferencing
    (Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2025-08-15) Wijegunarathna K; Stock K; Jones CB; Sila-Nowicka K; Moore A; O’Sullivan D; Adams B; Gahegan M
    Millions of biological sample records collected in the last few centuries archived in natural history collections are un-georeferenced. Georeferencing complex locality descriptions associated with these collection samples is a highly labour-intensive task collection agencies struggle with. None of the existing automated methods exploit maps that are an essential tool for georeferencing complex relations. We present preliminary experiments and results of a novel method that exploits multimodal capabilities of recent Large Multi-Modal Models (LMM). This method enables the model to visually contextualize spatial relations it reads in the locality description. We use a grid-based approach to adapt these auto-regressive models for this task in a zero-shot setting. Our experiments conducted on a small manually annotated dataset show impressive results for our approach (∼1 km Average distance error) compared to uni-modal georeferencing with Large Language Models and existing georeferencing tools. The paper also discusses the findings of the experiments in light of an LMM's ability to comprehend fine-grained maps. Motivated by these results, a practical framework is proposed to integrate this method into a georeferencing workflow.
  • Thumbnail Image
    Item
    Predicting Distance and Direction from Text Locality Descriptions for Biological Specimen Collections
    (Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2022-08-22) Liao R; Das PP; Jones CB; Aflaki N; Stock K; Ishikawa T; Fabrikant SI; Winter S
    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%.
  • Thumbnail Image
    Item
    Speaking of Location: Communicating about Space with Geospatial Natural Language
    (CEUR-WS.org, 2019-09-23) Stock K; Jones CB; Tenbrink T; Stock K; Jones CB; Tenbrink T
    Speaking of Location 2019 is the second edition of the Speaking of Location workshop series, which aims to foster transdisciplinary research to address the problem of automatic interpretation and generation of geospatial natural language. This introduction to the workshop proceedings provides background, discussing the definition and nature of geospatial natural language, presenting the papers contained in the proceedings volume, and situating them within the theoretical framework of The Semantic Pyramid, which is also described.
  • Thumbnail Image
    Item
    The Koja Web Mapping Application for Context-sensitive Natural Language Spatial Querying
    (CEUR Team, 2023-01-01) Aflaki N; Stock K; Jones CB; Guesgen H; Fukuzawa Y; Morley J; Hu X; Hu Y; Resch B; Kersten J; Stock K
    The locations of objects are often described in natural language relative to some other object using vague and context-sensitive spatial relation terms (e.g. theatre near Trafalgar Square). Koja is a web map application that predicts the distance between a location and reference object based on the spatial relation term specified by the user and language and contextual features. That distance is used to retrieve objects of the specified type within a range of the distance. They are displayed through a map interface to make the process more intuitive and user-friendly.
  • Thumbnail Image
    Item
    What Do You Mean You're in Trafalgar Square? Comparing Distance Thresholds for Geospatial Prepositions
    (Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2022-09-01) Aflaki N; Stock K; Jones CB; Guesgen H; Morley J; Fukuzawa Y; Ishikawa T; Fabrikant SI; Winter S
    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.