AAAI Publications, Second AAAI Conference on Human Computation and Crowdsourcing

Font Size: 
Combining Non-Expert and Expert Crowd Work to Convert Web APIs to Dialog Systems
Ting-Hao K. Huang, Walter S. Lasecki, Alan L. Ritter, Jeffrey P. Bigham

Last modified: 2014-09-05

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.

Keywords


API; crowd-powered interface

References


[1] Bernstein, M., and et al. 2010. Soylent: a word processorwith a crowd inside. In UIST.

[2] Bigham, J. P.; et; and al. 2010. Vizwiz: nearly real-timeanswers to visual questions. In UIST.

[3] Lasecki, W. S., and et al. 2013. Chorus: a crowd-poweredconversational assistant. In UIST.

[4] Von Ahn, L., and Dabbish, L. 2004. Labeling images witha computer game. In CHI.


Full Text: PDF