SynTOD: Augmented Response Synthesis for Robust End-to-End Task-Oriented Dialogue System

Nguyen Quang Chieu, Quang-Minh Tran, Khac-Hoai Nam Bui


Abstract
Task-oriented dialogue (TOD) systems are introduced to solve specific tasks, which focus on training multiple tasks such as language understanding, tracking states, and generating appropriate responses to help users achieve their specific goals. Currently, one of the remaining challenges in this emergent research field is the capability to produce more robust architectures fine-tuned for end-to-end TOD systems. In this study, we consider this issue by exploiting the ability of pre-trained models to provide synthesis responses, which are then used as the input for the fine-tuned process. The main idea is to overcome the gap between the training process and inference process during fine-tuning end-to-end TOD systems. The experiment on Multiwoz datasets shows the effectiveness of our model compared with strong baselines in this research field. The source code is available for further exploitation.
Anthology ID:
2024.lrec-main.1346
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
15493–15499
Language:
URL:
https://aclanthology.org/2024.lrec-main.1346
DOI:
Bibkey:
Cite (ACL):
Nguyen Quang Chieu, Quang-Minh Tran, and Khac-Hoai Nam Bui. 2024. SynTOD: Augmented Response Synthesis for Robust End-to-End Task-Oriented Dialogue System. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15493–15499, Torino, Italia. ELRA and ICCL.
Cite (Informal):
SynTOD: Augmented Response Synthesis for Robust End-to-End Task-Oriented Dialogue System (Chieu et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1346.pdf