Bridging the Gap: Generating a Comprehensive Biomedical Knowledge Graph Question Answering Dataset

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

Despite the plethora of resources such as large-scale corpora and manually curated Knowledge Graphs (KGs), the ability to perform reasoning with natural language inputs over biomedical graphs remains challenging due to insufficient training data. We propose a novel method for automatically constructing a Biomedical Knowledge Graph Question Answering (BioKGQA) dataset sourced from PrimeKG, the largest precision medicine-oriented KG. In total, we create 85,368 question-answer pairs along with their respective SPARQL queries. Our approach generates a diverse array of contextually relevant questions covering a wide spectrum of biomedical concepts and levels of complexity. We evaluate our method based on automatic metrics alongside manual annotations. We establish novel standards tailored for KGQA systems to highlight the linguistic correctness and semantical faithfulness of the generated questions based on extracted KG facts. The compiled dataset – PrimeKGQA – serves as a valuable benchmarking resource for advancing knowledge-driven biomedical research and evaluating KGQA systems.
OriginalspracheEnglisch
TitelECAI 2024 : 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain; including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024), Proceedings
HerausgeberUlle Endriss, Francisco S. Melo, Kerstin Bach, Alberto José Bugarín Diz, Jose Maria Alonso-Moral, Senén Barro, Fredrik Heintz
Anzahl der Seiten8
ErscheinungsortAmsterdam
VerlagIOS Press BV
Erscheinungsdatum16.10.2024
Seiten1198-1205
ISBN (elektronisch)978-1-64368-548-9
DOIs
PublikationsstatusErschienen - 16.10.2024
Veranstaltung27th European Conference on Artificial Intelligence - ECAI 2024: "Celebrating the past. Inspiring the future" - University of Santiago de Compostela., Santiago de Compostela, Spanien
Dauer: 19.10.202424.10.2024
Konferenznummer: 27
https://www.ecai2024.eu/

Bibliographische Notiz

Publisher Copyright:
© 2024 The Authors.

DOI

Zuletzt angesehen

Publikationen

  1. Segment Introduction
  2. Resource extraction technologies - is a more responsible path of development possible?
  3. An innovative efficiency of incubator to enhance organization supportive business using machine learning approach
  4. GENESIS - A generic RDF data access interface
  5. Hybrid modelling by machine learning corrections of analytical model predictions towards high-fidelity simulation solutions
  6. Support vector machines with example dependent costs
  7. Water quantity and quality dynamics of the THC - Tuyamuyun hydroengineering complex - and implications for reservoir operation
  8. Automating SPARQL Query Translations between DBpedia and Wikidata
  9. Detection of significant tracer gases by means of polymer gas sensors
  10. Toward a lifespan metric of reading fluency
  11. Biodiversity in space and time - towards a grid mapping for Mongolia
  12. Exploring Management Control Systems for Biodiversity
  13. Model Predictive Control for Energy Optimization in Generators/Motors as Well as Converters and Inverters for Futuristic Integrated Power Networks
  14. The end of certainties
  15. Mit Pixel und Korn
  16. Temperature changes using excimer laser irradiation in a cochlear model
  17. Interplay of formative assessment and instructional quality—interactive effects on students’ mathematics achievement
  18. Auditors' Perceptions of Client Firms
  19. How to Explain Major Policy Change Towards Sustainability? Bringing Together the Multiple Streams Framework and the Multilevel Perspective on Socio-Technical Transitions to Explore the German “Energiewende”
  20. Global Governance and the Interplay of Coordination and Contestation
  21. Inequality in the Transition from Primary to Secondary School
  22. Effect of Bleaching on the Elution of Monomers from Modern Dental Composite Materials
  23. Question Answering Mediated by Visual Clues and Knowledge Graphs
  24. Ähnlichkeit mit unähnlichen Mitteln