Combining Non-Expert and Expert Crowd Work to ConvertWeb APIs to Dialog Systems

Ting Hao K. Huang, Walter S. Lasecki, Alan L. Ritter, Jeffrey P. Bigham

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Thousands of web APIs expose data and services that would be useful to access with natural dialog, from weather and sports to Twitter and movies. The process of adapting each API to a robust dialog system is difficult and time-consuming, as it requires not only programming but also anticipating what is mostly likely to be asked and how it is likely to be asked. We present a crowd-powered system able to generate a natural language interface for arbitrary web APIs from scratch without domain-dependent training data or knowledge. Our approach combines two types of crowd workers: non-expert Mechanical Turk workers interpret the functions of the API and elicit information from the user, and expert oDesk workers provide a minimal sufficient scaffolding around the API to allow us to make general queries. We describe our multi-stage process and present results for each stage.

Original languageEnglish (US)
Title of host publicationProceedings of the 2nd AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2014
EditorsJeffrey P. Bigham, David Parkes
PublisherAAAI press
Pages22-23
Number of pages2
ISBN (Electronic)9781577356820
StatePublished - Nov 5 2014
Event2nd AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2014 - Pittsburgh, United States
Duration: Nov 2 2014Nov 4 2014

Publication series

NameProceedings of the 2nd AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2014

Conference

Conference2nd AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2014
Country/TerritoryUnited States
CityPittsburgh
Period11/2/1411/4/14

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Human-Computer Interaction

Cite this