DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation

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

Authors

Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both humanlike and informative responses in this setting. Recent research primarily focused on various knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured. In this paper, we go one step further and demonstrate how the structural information of a knowledge graph can improve the system's inference capabilities. Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-theart methods on several standard benchmark datasets.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics : NAACL 2022 - Findings
Number of pages15
PublisherAssociation for Computational Linguistics (ACL)
Publication date01.01.2022
Pages2557-2571
ISBN (electronic)9781955917766
DOIs
Publication statusPublished - 01.01.2022
Externally publishedYes
Event2022 Findings of the Association for Computational Linguistics - NAACL 2022 - Online + Hyatt Regency Seattle, Seattle, United States
Duration: 10.07.202215.07.2022
https://2022.naacl.org/downloads/handbook-final-v2.pdf
https://aclanthology.org/2022.findings-naacl.0/

Bibliographical note

Publisher Copyright:
© Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

Recently viewed

Publications

  1. Umweltmanagement in deutschen Unternehmen
  2. Schreibkonzepte von Grundschulkindern
  3. Spatial patterns of cultural ecosystem services provision in Southern Patagonia
  4. Acute effects of resistance training at different range of motions on plantar flexion mechanical properties and force
  5. Bruderpaar der Literatur
  6. Network-based analysis of Lagrangian transport and mixing
  7. Einführung
  8. Do We Need to Use an Accountant? The Sales Growth and Survival Benefits to Family SMEs
  9. Mathematical Prerequisites for STEM Programs
  10. Professional Service Firms, Knowledge-based Competition and the Heterarchical Organization Form
  11. Informatik und Nachhaltigkeitsmanagement
  12. Environmental Management Accounting and the Opportunity Cost of Neglecting Environmental Protection
  13. Die Problematik Granels
  14. Collaborative epistemic writing and writing-to-learn in mathematics
  15. IGLU
  16. Cultural Practices, Norms, and Values
  17. Weitblick statt Glaskugel?
  18. Ergebnisse einer Validierungsstudie zum DaZKom-Testinstrument
  19. The Maternal in Drag
  20. Towards a green and sustainable fruit waste valorisation model in Brazil
  21. New ideas for modern phytosociological monographs
  22. §43 VwGO [Feststellungsklage]
  23. Wie WIR unsere Welt globalisieren
  24. Ombuds- und Beschwerdestellen in der Kinder- und Jugendhilfe
  25. Normative Balance and Electoral Reform
  26. Zukünftiges Engagement der Studierendeninitiative Greening the University - wie es weiter geht
  27. Organizational ambidexterity and student achievement
  28. Imagined Geography
  29. Enhanced granular medium-based tube and hollow profile press hardening
  30. The Role of AI in Serious Games and Gamification for Health
  31. Abschied von gestern
  32. Bodensaure Eichen- und Eichenmischwälder Europas
  33. Overview of the Aggregate Results of the International Corporate Sustainability Barometer
  34. Emotionale Kompetenz und Emotionsarbeit in der Personalentwicklung
  35. What Kind of Veto Player Is the Italian Senate?