95% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Earth Sci.
Sec. Geoinformatics
Volume 13 - 2025 | doi: 10.3389/feart.2025.1530004
Assessing Named Entity Recognition by using Geosciences Domain Schemas: The case of Mineral Systems
Provisionally accepted
Sandra Paula Villacorta Chambi 1*
Mark Lindsay 1
Jens Klump 1
Klaus Gessner 2 Erin Gray 2 Helen McFarlane 1- 1 Mineral Resources - CSIRO, Kensington, Australia
- 2 Geological Survey of Western Australia, East Perth, Western Australia, Australia
Named Entity Recognition (NER) is essential for extracting and classifying specialized domain terms from textual data. Schemas provide structured frameworks by defining relevant entity classes and relationships, enabling computer systems to process discipline-specific terminology accurately. This study introduces the Schema for Mineral Systems (SMS), developed to evaluate NER accuracy in geoscientific texts on mineral systems, with nine geological and five general entity classes. SMS was created through domain characterization, word disambiguation, taxonomy development, and expert input to address the complexity of geological terminology. Domain-specific dictionaries and schema-linked annotations facilitated the identification of unique terms in mineral systems, while expert validation highlighted the importance of iterative verification to improve NER model performance. Applied to corpora on iron and lithium deposits in Western Australia, SMS use demonstrates the challenges of context-specific schemas in enhancing specialized knowledge extraction and accurate entity recognition in complex domains.
Keywords: Knowledge Management, nlp, ner, geological terminology, ontologies
Received: 18 Nov 2024; Accepted: 31 Mar 2025.
Copyright: © 2025 Villacorta Chambi, Lindsay, Klump, Gessner, Gray and McFarlane. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Sandra Paula Villacorta Chambi, Mineral Resources - CSIRO, Kensington, Australia
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.