Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
This work addresses the issue of incomplete user requests in task-oriented dialogue systems for developers and researchers, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of limited domain API coverage in task-oriented dialogue systems by incorporating external unstructured knowledge sources, resulting in an augmented dataset and baseline models for three defined sub-tasks.
Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by the APIs. In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources. We define three sub-tasks: knowledge-seeking turn detection, knowledge selection, and knowledge-grounded response generation, which can be modeled individually or jointly. We introduce an augmented version of MultiWOZ 2.1, which includes new out-of-API-coverage turns and responses grounded on external knowledge sources. We present baselines for each sub-task using both conventional and neural approaches. Our experimental results demonstrate the need for further research in this direction to enable more informative conversational systems.