Abstract
Prior work has demonstrated that data augmentation is useful for improving dialogue state tracking. However, there are many types of user utterances, while the prior method only considered the simplest one for augmentation, raising the concern about poor generalization capability. In order to better cover diverse dialogue acts and control the generation quality, this paper proposes controllable user dialogue act augmentation (CUDA-DST) to augment user utterances with diverse behaviors. With the augmented data, different state trackers gain improvement and show better robustness, achieving the state-of-the-art performance on MultiWOZ 2.1.- Anthology ID:
- 2022.sigdial-1.5
- Volume:
- Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- September
- Year:
- 2022
- Address:
- Edinburgh, UK
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 53–61
- Language:
- URL:
- https://aclanthology.org/2022.sigdial-1.5
- DOI:
- Cite (ACL):
- Chun-Mao Lai, Ming-Hao Hsu, Chao-Wei Huang, and Yun-Nung Chen. 2022. Controllable User Dialogue Act Augmentation for Dialogue State Tracking. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 53–61, Edinburgh, UK. Association for Computational Linguistics.
- Cite (Informal):
- Controllable User Dialogue Act Augmentation for Dialogue State Tracking (Lai et al., SIGDIAL 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.sigdial-1.5.pdf
- Code
- miulab/cuda-dst