TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
This addresses the challenge of enabling dialogue systems to adapt to new tasks while preserving prior knowledge, which is incremental as it builds on existing continual learning methods for a specific domain.
The paper tackles the problem of catastrophic forgetting and knowledge transfer in continual dialogue state tracking by introducing TaSL, a framework for task skill localization and consolidation, which achieves significant performance improvements over state-of-the-art methods without relying on memory replay.
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.