TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation

TL;DR

TaSL is a novel continual dialogue state tracking framework that localizes and consolidates task skills to enable effective knowledge transfer and mitigate catastrophic forgetting without memory replay.

Contribution

It introduces a group-wise technique for task skill localization and a fine-grained consolidation strategy to improve continual DST performance.

Findings

Significant performance improvements over state-of-the-art methods.

Effective knowledge transfer without memory replay.

Balances knowledge preservation and learning new tasks.

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 over existing state-of-the-art methods. The source code is provided for reproducibility.