TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan Shi, Bo Liu, Xiao-Ming Wu
Abstract
A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL, with a 7.6% absolute increase in Avg. JGA and an 11% absolute rise in BWT metrics over existing state-of-the-art methods. The source code is provided for reproducibility.- Anthology ID:
- 2024.acl-long.69
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1266–1279
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.69
- DOI:
- Cite (ACL):
- Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan Shi, Bo Liu, and Xiao-Ming Wu. 2024. TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1266–1279, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation (Feng et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.69.pdf