Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Experts
This work addresses the problem of scaling and performance bottlenecks in task-oriented dialogue systems for virtual assistants and automated services, representing an incremental improvement over existing methods.
The authors tackled the limitations of pre-trained language models in task-oriented dialogue systems by proposing SMETOD, a module-based mixture-of-experts approach that achieves state-of-the-art performance on intent prediction, dialogue state tracking, and response generation benchmarks while improving inference efficiency and correctness.
Task-oriented dialogue systems are broadly used in virtual assistants and other automated services, providing interfaces between users and machines to facilitate specific tasks. Nowadays, task-oriented dialogue systems have greatly benefited from pre-trained language models (PLMs). However, their task-solving performance is constrained by the inherent capacities of PLMs, and scaling these models is expensive and complex as the model size becomes larger. To address these challenges, we propose Soft Mixture-of-Expert Task-Oriented Dialogue system (SMETOD) which leverages an ensemble of Mixture-of-Experts (MoEs) to excel at subproblems and generate specialized outputs for task-oriented dialogues. SMETOD also scales up a task-oriented dialogue system with simplicity and flexibility while maintaining inference efficiency. We extensively evaluate our model on three benchmark functionalities: intent prediction, dialogue state tracking, and dialogue response generation. Experimental results demonstrate that SMETOD achieves state-of-the-art performance on most evaluated metrics. Moreover, comparisons against existing strong baselines show that SMETOD has a great advantage in the cost of inference and correctness in problem-solving.