Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups

Zhiyang Qi, Michimasa Inaba


Abstract
This study addresses the interaction challenges encountered by spoken dialogue systems (SDSs) when engaging with users who exhibit distinct conversational behaviors, particularly minors, in scenarios where data are scarce. We propose a novel data augmentation framework to enhance SDS performance for user groups with limited resources. Our approach leverages a large language model (LLM) to extract speaker styles and a pre-trained language model (PLM) to simulate dialogue act history. This method generates enriched and personalized dialogue data, facilitating improved interactions with unique user demographics. Extensive experiments validate the efficacy of our methodology, highlighting its potential to foster the development of more adaptive and inclusive dialogue systems.
Anthology ID:
2024.sigdial-1.14
Volume:
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2024
Address:
Kyoto, Japan
Editors:
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, Koji Inoue, Shikib Mehri, David Howcroft, Kazunori Komatani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
159–171
Language:
URL:
https://aclanthology.org/2024.sigdial-1.14
DOI:
10.18653/v1/2024.sigdial-1.14
Bibkey:
Cite (ACL):
Zhiyang Qi and Michimasa Inaba. 2024. Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 159–171, Kyoto, Japan. Association for Computational Linguistics.
Cite (Informal):
Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups (Qi & Inaba, SIGDIAL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigdial-1.14.pdf