Using Textual Interface to Align External Knowledge for End-to-End Task-Oriented Dialogue Systems
This work addresses a specific problem in dialogue systems for improving response quality and task success, representing an incremental advancement.
The paper tackles the misalignment between agent responses and external knowledge in end-to-end task-oriented dialogue systems by proposing a novel paradigm using a textual interface, which results in more natural final responses and a higher task success rate compared to previous models.
Traditional end-to-end task-oriented dialogue systems have been built with a modularized design. However, such design often causes misalignment between the agent response and external knowledge, due to inadequate representation of information. Furthermore, its evaluation metrics emphasize assessing the agent's pre-lexicalization response, neglecting the quality of the completed response. In this work, we propose a novel paradigm that uses a textual interface to align external knowledge and eliminate redundant processes. We demonstrate our paradigm in practice through MultiWOZ-Remake, including an interactive textual interface built for the MultiWOZ database and a correspondingly re-processed dataset. We train an end-to-end dialogue system to evaluate this new dataset. The experimental results show that our approach generates more natural final responses and achieves a greater task success rate compared to the previous models.