"Is there anything else I can help you with?": Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent
This addresses the problem of enabling more natural human-like interactions in conversational agents for users, though it is incremental as it builds on existing crowd-sourcing approaches.
The paper tackled the limitations of existing conversational assistants by deploying a crowd-powered system called Chorus, which recruited workers on demand to generate responses, resulting in 59 users engaging in 320 conversational sessions over the first month.
Intelligent conversational assistants, such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to interact with the underlying system. To address this problem, we developed a crowd-powered conversational assistant, Chorus, and deployed it to see how users and workers would interact together when mediated by the system. Chorus sophisticatedly converses with end users over time by recruiting workers on demand, which in turn decide what might be the best response for each user sentence. Up to the first month of our deployment, 59 users have held conversations with Chorus during 320 conversational sessions. In this paper, we present an account of Chorus' deployment, with a focus on four challenges: (i) identifying when conversations are over, (ii) malicious users and workers, (iii) on-demand recruiting, and (iv) settings in which consensus is not enough. Our observations could assist the deployment of crowd-powered conversation systems and crowd-powered systems in general.