Abstract
Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end task-oriented dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics.- Anthology ID:
- 2024.findings-naacl.46
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2024
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Kevin Duh, Helena Gomez, Steven Bethard
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 727–735
- Language:
- URL:
- https://aclanthology.org/2024.findings-naacl.46
- DOI:
- Cite (ACL):
- Nalin Kumar and Ondrej Dusek. 2024. LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 727–735, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems (Kumar & Dusek, Findings 2024)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2024.findings-naacl.46.pdf