TY - GEN
T1 - Evorus
T2 - 2018 CHI Conference on Human Factors in Computing Systems, CHI 2018
AU - Huang, Ting Hao
AU - Chang, Joseph Chee
AU - Bigham, Jeffrey P.
N1 - Publisher Copyright:
© 2018 Copyright is held by the owner/author(s).
PY - 2018/4/20
Y1 - 2018/4/20
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85046972237&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046972237&partnerID=8YFLogxK
U2 - 10.1145/3173574.3173869
DO - 10.1145/3173574.3173869
M3 - Conference contribution
AN - SCOPUS:85046972237
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
Y2 - 21 April 2018 through 26 April 2018
ER -