Speaking with the crowd

Walter S. Lasecki, Rachel Wesley, Anand Kulkarni, Jeffrey P. Bigham

Abstract

Automated systems are not yet able to engage in a robust dialogue with users due the complexity and ambiguity of natural language. However, humans can easily converse with one another and maintain a shared history of past interactions. In this paper, we introduce Chorus, a system that enables real-time, two-way natural language conversation between an end user and a crowd acting as a single agent. Chorus is capable of maintaining a consistent, on-topic conversation with end users across multiple sessions, despite constituent individuals perpetually joining and leaving the crowd. This is enabled by using a curated shared dialogue history. Even though crowd members are constantly providing input, we present users with a stream of dialogue that appears to be from a single conversational partner. Experiments demonstrate that dialogue with Chorus displays elements of conversational memory and interaction consistency. Workers were able to answer 84.6% of user queries correctly, demonstrating that crowd-powered communication interfaces can serve as a robust means of interacting with software systems.
BibTeX
@inproceedings{lasecki2012speaking,
  author = {Walter S. Lasecki and Rachel Wesley and Anand Kulkarni and Jeffrey P. Bigham},
  title = {{Speaking with the crowd}},
  booktitle = {Uist (adjunct Volume)},
  year = {2012},
  doi = {10.1145/2380296.2380310},
}

Loading related content...

Figure