Combining Non-Expert and Expert Crowd Work to Convert Web APIs to Dialog Systems

Authors

  • Ting-Hao Huang Carnegie Mellon University
  • Walter Lasecki University of Rochester
  • Alan Ritter The Ohio State University
  • Jeffrey Bigham Carnegie Mellon University

Keywords:

API, crowd-powered interface

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 languageinterface 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.

Downloads

Published

2014-09-05

How to Cite

Huang, T.-H., Lasecki, W., Ritter, A., & Bigham, J. (2014). Combining Non-Expert and Expert Crowd Work to Convert Web APIs to Dialog Systems. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 2(1). Retrieved from https://ojs.aaai.org/index.php/HCOMP/article/view/13200