Beyond class A: a proposal for automatic evaluation of discourse
HLT '90 Proceedings of the workshop on Speech and Natural Language
PARADISE: a framework for evaluating spoken dialogue agents
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Labeling images with a computer game
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Human computation
TurKit: human computation algorithms on mechanical turk
UIST '10 Proceedings of the 23nd annual ACM symposium on User interface software and technology
Soylent: a word processor with a crowd inside
UIST '10 Proceedings of the 23nd annual ACM symposium on User interface software and technology
VizWiz: nearly real-time answers to visual questions
UIST '10 Proceedings of the 23nd annual ACM symposium on User interface software and technology
Turkomatic: automatic recursive task and workflow design for mechanical turk
CHI '11 Extended Abstracts on Human Factors in Computing Systems
Real-time crowd control of existing interfaces
Proceedings of the 24th annual ACM symposium on User interface software and technology
Crowds in two seconds: enabling realtime crowd-powered interfaces
Proceedings of the 24th annual ACM symposium on User interface software and technology
CrowdForge: crowdsourcing complex work
Proceedings of the 24th annual ACM symposium on User interface software and technology
Answering search queries with CrowdSearcher
Proceedings of the 21st international conference on World Wide Web
Human computation tasks with global constraints
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Direct answers for search queries in the long tail
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Real-time captioning by groups of non-experts
Proceedings of the 25th annual ACM symposium on User interface software and technology
Real-time crowd labeling for deployable activity recognition
Proceedings of the 2013 conference on Computer supported cooperative work
Proceedings of the 2013 conference on Computer supported cooperative work
Answering visual questions with conversational crowd assistants
Proceedings of the 15th International ACM SIGACCESS Conference on Computers and Accessibility
Answering visual questions with conversational crowd assistants
Proceedings of the 15th International ACM SIGACCESS Conference on Computers and Accessibility
Information extraction and manipulation threats in crowd-powered systems
Proceedings of the 17th ACM conference on Computer supported cooperative work & social computing
Hi-index | 0.00 |
Despite decades of research attempting to establish conversational interaction between humans and computers, the capabilities of automated conversational systems are still limited. In this paper, we introduce Chorus, a crowd-powered conversational assistant. When using Chorus, end users converse continuously with what appears to be a single conversational partner. Behind the scenes, Chorus leverages multiple crowd workers to propose and vote on responses. A shared memory space helps the dynamic crowd workforce maintain consistency, and a game-theoretic incentive mechanism helps to balance their efforts between proposing and voting. Studies with 12 end users and 100 crowd workers demonstrate that Chorus can provide accurate, topical responses, answering nearly 93% of user queries appropriately, and staying on-topic in over 95% of responses. We also observed that Chorus has advantages over pairing an end user with a single crowd worker and end users completing their own tasks in terms of speed, quality, and breadth of assistance. Chorus demonstrates a new future in which conversational assistants are made usable in the real world by combining human and machine intelligence, and may enable a useful new way of interacting with the crowds powering other systems.