Analyzing geographic questions using embedding-based topic modeling

J Yang, H Jang, K Yu - ISPRS International Journal of Geo-Information, 2023 - mdpi.com
Recently, open-domain question-answering systems have achieved tremendous progress
because of developments in large language models (LLMs), and have successfully been …

Correctness Comparison of ChatGPT‐4, Gemini, Claude‐3, and Copilot for Spatial Tasks

HH Hochmair, L Juhász, T Kemp - Transactions in GIS, 2024 - Wiley Online Library
Generative AI including large language models (LLMs) has recently gained significant
interest in the geoscience community through its versatile task‐solving capabilities including …

LLM-powered natural language text processing for ontology enrichment

A Mukanova, M Milosz, A Dauletkaliyeva, A Nazyrova… - 2024 - rep.enu.kz
This paper describes a method and technology for processing natural language texts and
extracting data from the text that correspond to the semantics of an ontological model. The …

Pragmatic GeoAI: Geographic information as externalized practice

S Scheider, KF Richter - KI-Künstliche Intelligenz, 2023 - Springer
Current artificial intelligence (AI) approaches to handle geographic information (GI) reveal a
fatal blindness for the information practices of exactly those sciences whose methodological …

Semantic complexity of geographic questions-A comparison in terms of conceptual transformations of answers

E Nyamsuren, H Xu, EJ Top… - AGILE …, 2023 - agile-giss.copernicus.org
There is an increasing trend of applying AIbased automated methods to geoscience
problems. An important example is a geographic question answering (geoQA) focused on …

What Is a Spatio-Temporal Model Good For?: Validity as a Function of Purpose and the Questions Answered by a Model

S Scheider, JA Verstegen - 16th International Conference on …, 2024 - drops.dagstuhl.de
The concept of validity is a cornerstone of science. Given this central role, it is somewhat
surprising to find that validity remains a rather obscure concept. Unfortunately, the term is …

Algebra of core concept transformations. Procedural meta-data for geographic information

N Steenbergen, E Top, S Scheider, E Nyamsuren - 2022 - osf.io
Transformations are essential for dealing with geographic information. They are involved not
only in converting between geodata formats and reference systems, but also in turning …

Study of Grammar Structure in Thesis Abstracts of Nursing Students of Stikes Ngudia Husada Madura

DP Irianto, E Nurniati - Indo-MathEdu Intellectuals …, 2023 - ejournal.indo-intellectual.id
This study discusses the analysis of grammar structure in thesis abstracts of nursing
program students at the Ngudia Husada Madura Student of Health Sciences (STIKES). The …

Comparing deep learning methods for concept recognition in geo-analytic questions

A Kandylas - 2022 - studenttheses.uu.nl
Named Entity Recognition (NER) is an important process of NLP systems for relation
extraction, information retrieval and machine translation. Although various NER systems …

A Pipeline to Construct a Real-World Question and GeoSPARQL Query Dataset for Geo-Analytical Question Answering over OpenStreetMap Data

EH Jeong, TJ Yang, JH Yang, K Yu - 한국측량학회지, 2022 - dbpia.co.kr
An immense pull of data led to the growth of the QA (Question Answering) system. With the
growth of comprehensive QA systems, KBQA (QA over Knowledge Base) demonstrates an …