University of Cambridge > > NLIP Seminar Series > Duolingo: Improving Language Learning and Assessment with A.I.

Duolingo: Improving Language Learning and Assessment with A.I.

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Andrew Caines.

Consider this paradox: If education is the key to getting out of poverty and achieving greater social equality, why is high-quality education so often expensive and inaccessible to those who need it most? Artificial intelligence will never replace great teachers, but until everyone in the world has equal access to great teachers, AI and machine learning provide a tremendous opportunity to scale quality education to everyone who needs it.

In this talk, I will describe Duolingo’s mission to combine AI-driven learning technology with a unique business model, enabling us to provide language instruction for free and bring us closer to a more engaged, empathetic, and educated world. Duolingo has more than 300 million users from virtually every country in the world. Their lesson data can be harnessed to develop novel technologies, such as personalized practice sessions and data-driven language assessments like the Duolingo English Test. These efforts combine learner data with machine learning, computational linguistics, and psychometrics to improve educational and motivational outcomes, crossing socioeconomic barriers from America to Zimbabwe.

Burr Settles is Research Director at Duolingo, the world’s largest language-learning platform. He is also the author of Active Learning, a text on adaptive machine learning algorithms. His research has been published in major AI venues such as Cognitive Science, NeurIPS, ICML , and AAAI , and has been covered by The New York Times, Forbes, WIRED , and BBC . Previously, Burr was a postdoc at Carnegie Mellon and earned a PhD from UW-Madison.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity