Structuring Sustainability Reports for Environmental Standards with LLMs guided by Ontology

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Following the introduction of the European Sustainability Reporting Standard (ESRS), companies will have to adapt to a new policy and provide mandatory sustainability reports. However, implementing such reports entails a challenge, such as the comprehension of a large number of textual information from various sources. This task can be accelerated by employing Large Language Models (LLMs) and ontologies to effectively model the domain knowledge. In this study, we extended an existing ontology to model ESRS Topical Standard for disclosure. The developed ontology would enable automated reasoning over the data and assist in constructing Knowledge Graphs (KGs). Moreover, the proposed ontology extension would also help to identify gaps in companies’ sustainability reports with regard to the ESRS requirements. Additionally, we extracted knowledge from corporate sustainability reports via LLMs guided with a proposed ontology and developed their KG representation.

Original languageEnglish
Title of host publicationClimateNLP 2024 - 1st Workshop on Natural Language Processing Meets Climate Change, Proceedings of the Workshop
EditorsDominik Stammbach, Jingwei Ni, Tobias Schimanski, Kalyan Dutia, Alok Singh, Julia Bingler, Christophe Christiaen, Neetu Kushwaha, Veruska Muccione, Saeid A. Vaghefi, Markus Leippold
Number of pages10
PublisherAssociation for Computational Linguistics (ACL)
Publication date2024
Pages168-177
ISBN (electronic)979-8-89176-159-9
Publication statusPublished - 2024
Event1st Workshop on Natural Language Processing Meets Climate Change - ClimateNLP 2024 - Bangkok, Thailand
Duration: 16.08.202416.08.2024
Conference number: 1
https://nlp4climate.github.io/

Bibliographical note

Publisher Copyright:
©2024 Association for Computational Linguistics.

Recently viewed

Publications

  1. A path to clean water
  2. How Big Does Big Data Need to Be?
  3. Forest structure and heterogeneity increase diversity and alter composition of host–parasitoid networks
  4. Usage pattern-based exposure screening as a simple tool for the regional priority-setting in environmental risk assessment of veterinary antibiotics
  5. Release of monomers from four different composite materials after halogen and LED curing
  6. Modelling scenarios to identify a combined sediment-water management strategy for the large reservoirs of the Tuyamuyun hydro-complex
  7. Consular Assistance: Rights, Remedies, and Responsibility Comments on the ICJ's Judgment in the LaGrand Case
  8. Understanding Similarities and Differences of Digital Health Platforms
  9. Effect of salinity-changing rates on filtration activity of mussels from two sites within the Baltic Mytilus hybrid zone
  10. Der "fachdidaktische Code" der Lebenswelt- und/oder (?) Situationsorientierung
  11. Putting Architecture in its Social Space: the Fields and Skills of Planning Maastricht
  12. Das relationale Apriori Wiens / Das städtische Apriori des Relationalismus
  13. Monitoring of methotrexate chlorination in water
  14. Time for the Environment: The Tutzing Time Ecology Project
  15. Evidence for singlet state β cleavage in the photoreaction of α-(2,6-dimethoxyphenoxy)-acetophenone inferred from time-resolved CIDNP spectroscopy
  16. The complementary relationship of exploration and exploitation in professional service firms: An exploratory study of IT consulting firms
  17. Multivariate Optimization of Analytical Methodology and a First Attempt to an Environmental Risk Assessment of β-Blockers in Hospital Wastewater
  18. The rise and decline of regional power
  19. Modeling Interactions and Dependencies in Production Planning and Control
  20. How to specify the structure of substituted blade-like zigzag diamondoids
  21. X Machina and the World of Tomorrow