Artificial Intelligence with Humans in the LoopSpeaker: Gianluca Demartini – Queensland, Australia
Topic(s): Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing
Crowdsourcing is a novel approach used to obtain manual data processing and annotation at scale. This can be used to create Artificial Intelligence systems with humans in the loop that can support data pre-processing for training AI models or result post-processing to improve its quality.
In this talk, I will introduce the dynamics of the popular crowdsourcing platform Amazon MTurk and provide examples of its use to build hybrid human-machine systems. I will then present ZenCrowd: a human-in-the-loop system for entity linking and data integration showing how the use of human intelligence at scale in combination with machine-based algorithms may outperform traditional approaches. Finally, I will discuss how human factors influence the performance of such systems and which techniques can be used to improve their effectiveness.
About this LectureNumber of Slides: 40
Duration: 45 minutes
Languages Available: English
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.