A Framework for Adaptive Crowd Query Processing

Authors

  • Beth Trushkowsky University of California, Berkeley
  • Tim Kraska Brown University
  • Michael Franklin University of California, Berkeley

DOI:

https://doi.org/10.1609/hcomp.v1i1.13131

Abstract

Search engines can yield poor results for information retrieval tasks when they cannot interpret query predicates. Such predicates are better left for humans to evaluate. We propose an adaptive processing framework for deciding (a) which parts of a query should be processed by machines and (b) the order the crowd should process the remaining parts, optimizing for result quality and processing cost. We describe an algorithm and experimental results for the first framework component.

Downloads

Published

2013-11-03

How to Cite

Trushkowsky, B., Kraska, T., & Franklin, M. (2013). A Framework for Adaptive Crowd Query Processing. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 1(1), 74-75. https://doi.org/10.1609/hcomp.v1i1.13131

Issue

Vol. 1 (2013): First AAAI Conference on Human Computation and Crowdsourcing

Section

Works in Progress