Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.09857 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916374866034688 |
|---|---|
| author | Feng, Yujie Chu, Xu Xu, Yongxin Shi, Guangyuan Liu, Bo Wu, Xiao-Ming |
| author_facet | Feng, Yujie Chu, Xu Xu, Yongxin Shi, Guangyuan Liu, Bo Wu, Xiao-Ming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09857 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation Feng, Yujie Chu, Xu Xu, Yongxin Shi, Guangyuan Liu, Bo Wu, Xiao-Ming Computation and Language 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. |
| title | TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.09857 |