Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time

TL;DR

Evorus is a crowd-powered conversational assistant that progressively automates itself over time by integrating chatbots, reusing responses, and learning response approval, maintaining quality while reducing costs and latency.

Contribution

It introduces a self-automating architecture for crowd-powered chatbots, enabling easy integration of new automation and learning from interactions in a real deployment.

Findings

Evorus maintained conversation quality over 5 months.

The system successfully integrated automation to reduce costs.

It demonstrated self-improvement in a real-world deployment.

Abstract

Crowd-powered conversational assistants have been shown to be more robust than automated systems, but do so at the cost of higher response latency and monetary costs. A promising direction is to combine the two approaches for high quality, low latency, and low cost solutions. In this paper, we introduce Evorus, a crowd-powered conversational assistant built to automate itself over time by (i) allowing new chatbots to be easily integrated to automate more scenarios, (ii) reusing prior crowd answers, and (iii) learning to automatically approve response candidates. Our 5-month-long deployment with 80 participants and 281 conversations shows that Evorus can automate itself without compromising conversation quality. Crowd-AI architectures have long been proposed as a way to reduce cost and latency for crowd-powered systems; Evorus demonstrates how automation can be introduced successfully in a deployed system. Its architecture allows future researchers to make further innovation on the underlying automated components in the context of a deployed open domain dialog system.