Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking
This addresses the challenge of developing online dialogue systems that can learn continuously without performance degradation, though it appears incremental as it builds on existing continual learning methods.
The paper tackles the problem of continual learning in task-oriented dialogue systems to prevent forgetting old tasks while learning new ones, proposing TPEM which uses iterative pruning, expanding, and masking, and shows significantly improved results over strong competitors on seven tasks from three benchmark datasets.
This ability to learn consecutive tasks without forgetting how to perform previously trained problems is essential for developing an online dialogue system. This paper proposes an effective continual learning for the task-oriented dialogue system with iterative network pruning, expanding and masking (TPEM), which preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks. Specifically, TPEM (i) leverages network pruning to keep the knowledge for old tasks, (ii) adopts network expanding to create free weights for new tasks, and (iii) introduces task-specific network masking to alleviate the negative impact of fixed weights of old tasks on new tasks. We conduct extensive experiments on seven different tasks from three benchmark datasets and show empirically that TPEM leads to significantly improved results over the strong competitors. For reproducibility, we submit the code and data at: https://github.com/siat-nlp/TPEM