Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System
This work addresses the difficulty for non-experts in handling large parameter fine-tuning in dialogue systems, though it is incremental as it builds on existing adapter and reinforcement learning methods.
The paper tackles the challenge of debugging and fine-tuning end-to-end task-oriented dialogue systems by proposing task-optimized adapters that learn independently per task with few added parameters, achieving competitive performance on the MultiWOZ benchmark and state-of-the-art results on the DST task of the 2.2 dataset.
Task-Oriented Dialogue (TOD) systems are designed to carry out specific tasks by tracking dialogue states and generating appropriate responses to help users achieve defined goals. Recently, end-to-end dialogue models pre-trained based on large datasets have shown promising performance in the conversational system. However, they share the same parameters to train tasks of the dialogue system (NLU, DST, NLG), so debugging each task is challenging. Also, they require a lot of effort to fine-tune large parameters to create a task-oriented chatbot, making it difficult for non-experts to handle. Therefore, we intend to train relatively lightweight and fast models compared to PLM. In this paper, we propose an End-to-end TOD system with Task-Optimized Adapters which learn independently per task, adding only small number of parameters after fixed layers of pre-trained network. We also enhance the performance of the DST and NLG modules through reinforcement learning, overcoming the learning curve that has lacked at the adapter learning and enabling the natural and consistent response generation that is appropriate for the goal. Our method is a model-agnostic approach and does not require prompt-tuning as only input data without a prompt. As results of the experiment, our method shows competitive performance on the MultiWOZ benchmark compared to the existing end-to-end models. In particular, we attain state-of-the-art performance on the DST task of 2.2 dataset.