Continual Learning in Task-Oriented Dialogue Systems
This work addresses the challenge of continually adding new domains and functionalities to task-oriented dialogue systems without expensive retraining, which is a significant problem for developers and maintainers of such systems.
This paper proposes a continual learning benchmark for task-oriented dialogue systems across 37 domains and four settings. They found that their proposed adapter-based architectural method and a replay-based strategy performed comparably, but both were inferior to a multi-task learning baseline, indicating the difficulty of continual learning in this domain.
Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings, such as intent recognition, state tracking, natural language generation, and end-to-end. Moreover, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. Our experiments demonstrate that the proposed architectural method and a simple replay-based strategy perform comparably well but they both achieve inferior performance to the multi-task learning baseline, in where all the data are shown at once, showing that continual learning in task-oriented dialogue systems is a challenging task. Furthermore, we reveal several trade-offs between different continual learning methods in term of parameter usage and memory size, which are important in the design of a task-oriented dialogue system. The proposed benchmark is released together with several baselines to promote more research in this direction.