• Publications
  • Influence
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
TLDR
This work conducts mixed-method user studies on three datasets, where an AI with accuracy comparable to humans helps participants solve a task (explaining itself in some conditions), and observes complementary improvements from AI augmentation that were not increased by explanations.
Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols
TLDR
This work introduces ScholarPhi, an augmented reading interface with four novel features: tooltips that surface position-sensitive definitions from elsewhere in a paper, a filter over the paper that “declutters” it to reveal how the term or symbol is used across the paper, automatic equation diagrams that expose multiple definitions in parallel, and an automatically generated glossary of important terms and symbols.
Two Tools are Better Than One: Tool Diversity as a Means of Improving Aggregate Crowd Performance
TLDR
This paper introduces a novel crowdsourcing workflow that leverages multiple tools for the same task to increase output accuracy by reducing systematic error biases introduced by the tools themselves.
FourEyes: Leveraging Tool Diversity as a Means to Improve Aggregate Accuracy in Crowdsourcing
TLDR
A novel crowdsourcing approach that leverages tool diversity as a means of improving aggregate crowd performance and introduces a novel region-based error-correction method and additional in-depth evaluation of the proposed approach are provided.
WearMail: On-the-Go Access to Information in Your Email with a Privacy-Preserving Human Computation Workflow
TLDR
The impact of varying levels of obfuscation on result quality is explored, demonstrating that workers are able to deal with highly-obfuscated information nearly as well as with the original.
Towards More Robust Speech Interactions for Deaf and Hard of Hearing Users
TLDR
A better understanding of the challenges of deaf speech recognition is contributed and insights for future system development are provided, including the potential for groups to collectively exceed the performance of individuals.
FourEyes
TLDR
A novel crowdsourcing approach that leverages tool diversity as a means of improving aggregate crowd performance and introduces a novel region-based error-correction method and additional in-depth evaluation of the proposed approach are provided.
WearMail
Tool Diversity as a Means of Improving Aggregate Crowd Performance on an Object Segmentation Task
TLDR
This paper introduces an approach that leverages multiple segmentation tools for the same task to avoid systematic biases introduced by the tools themselves, and presents a series of studies that evaluate the feasibility of the approach and show that it is able to significantly improve aggregate accuracy in semantic image segmentation.
Experimental Crowd+AI Approaches to Track Accessibility Features in Sidewalk Intersections Over Time
TLDR
Three preliminary crowd+AI (Artificial Intelligence) prototypes are introduced to track changes in street intersection accessibility over time—specifically, curb ramps—and report on results from a pilot usability study.
...
1
2
...