2022/06/24 by Miaoran Li, Baolin Peng, Li, Miaoran +5 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #cs.AI #cs.CL #cs.IR
paper · pdf · doi:10.48550/arxiv.2206.12449
arxiv created 2022/06/24 · arxiv updated 2022/06/28
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.