OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience
This work addresses the need for conversational agents that can handle both task completion and information seeking, representing an incremental step by integrating existing tasks into a new framework.
The paper tackles the separation between task-oriented dialog and question answering by introducing Open-Book TOD, a unified task that combines both with access to explicit and implicit external knowledge, and demonstrates OPERA's superior performance over closed-book baselines, showing the value of both knowledge types.
Existing studies in conversational AI mostly treat task-oriented dialog (TOD) and question answering (QA) as separate tasks. Towards the goal of constructing a conversational agent that can complete user tasks and support information seeking, it is important to build a system that handles both TOD and QA with access to various external knowledge. In this work, we propose a new task, Open-Book TOD (OB-TOD), which combines TOD with QA task and expand external knowledge sources to include both explicit knowledge sources (e.g., the Web) and implicit knowledge sources (e.g., pre-trained language models). We create a new dataset OB-MultiWOZ, where we enrich TOD sessions with QA-like information seeking experience grounded on external knowledge. We propose a unified model OPERA (Open-book End-to-end Task-oriented Dialog) which can appropriately access explicit and implicit external knowledge to tackle the defined task. Experimental results demonstrate OPERA's superior performance compared to closed-book baselines and illustrate the value of both knowledge types.