TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
| Autor: | Feng, Yujie, Chu, Xu, Xu, Yongxin, Shi, Guangyuan, Liu, Bo, Wu, Xiao-Ming |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | 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 over existing state-of-the-art methods. The source code is provided for reproducibility. Comment: Accepted to ACL 2024 Main Conference. arXiv admin note: text overlap with arXiv:2408.05200 |
| Databáze: | arXiv |
| Externí odkaz: |
|