Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
This addresses the challenge of sparse and delayed rewards in RL for task-oriented dialogue systems, offering a more integrated approach, though it is incremental as it builds on existing RL methods.
The paper tackled the problem of reinforcement learning (RL) in task-oriented dialogue systems focusing only on generation tasks, neglecting understanding, by introducing step-by-step rewards for both understanding and generation to achieve balanced optimization. The result was enhanced performance, achieving new state-of-the-art results on three datasets and superior few-shot ability in low-resource settings.
Reinforcement learning (RL) is a powerful approach to enhance task-oriented dialogue (TOD) systems. However, existing RL methods tend to mainly focus on generation tasks, such as dialogue policy learning (DPL) or response generation (RG), while neglecting dialogue state tracking (DST) for understanding. This narrow focus limits the systems to achieve globally optimal performance by overlooking the interdependence between understanding and generation. Additionally, RL methods face challenges with sparse and delayed rewards, which complicates training and optimization. To address these issues, we extend RL into both understanding and generation tasks by introducing step-by-step rewards throughout the token generation. The understanding reward increases as more slots are correctly filled in DST, while the generation reward grows with the accurate inclusion of user requests. Our approach provides a balanced optimization aligned with task completion. Experimental results demonstrate that our approach effectively enhances the performance of TOD systems and achieves new state-of-the-art results on three widely used datasets, including MultiWOZ2.0, MultiWOZ2.1, and In-Car. Our approach also shows superior few-shot ability in low-resource settings compared to current models.