On Automating Conversations
This work addresses the challenge of creating automated conversational assistants for real-world use, though it is incremental as it builds on existing crowd-powered approaches.
The authors tackled the problem of automating conversations by developing and deploying Chorus, a system that blends human computation with AI, which engaged over 420 users in more than 2,200 conversation sessions over two years to help with everyday tasks.
From 2016 to 2018, we developed and deployed Chorus, a system that blends real-time human computation with artificial intelligence (AI) and has real-world, open conversations with users. We took a top-down approach that started with a working crowd-powered system, Chorus, and then created a framework, Evorus, that enables Chorus to automate itself over time. Over our two-year deployment, more than 420 users talked with Chorus, having over 2,200 conversation sessions. This line of work demonstrated how a crowd-powered conversational assistant can be automated over time, and more importantly, how such a system can be deployed to talk with real users to help them with their everyday tasks. This position paper discusses two sets of challenges that we explored during the development and deployment of Chorus and Evorus: the challenges that come from being an "agent" and those that arise from the subset of conversations that are more difficult to automate.