LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems

Nalin Kumar, Ondrej Dusek


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:
10.18653/v1/2024.findings-naacl.46
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.46.pdf