Seokhwan Kim author Mihail Eric author Karthik Gopalakrishnan author Behnam Hedayatnia author Yang Liu author Dilek Hakkani-Tur author 2020-jul text Association for Computational Linguistics 1st virtual meeting conference publication 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. kim-etal-2020-beyond https://www.aclweb.org/anthology/2020.sigdial-1.35 2020-jul 278 289