| CARVIEW |
Duolingo Research
Science powers our mission to make language education free and accessible to everyone.
About Us
With more than 500 million learners, Duolingo has the world's largest collection of language-learning data at its fingertips. This allows us to build unique systems, uncover new insights about the nature of language and learning, and apply existing theories at scales never before seen. We are also committed to sharing publications and data with the broader research community.
Publications
-
Jump-Starting Item Parameters for Adaptive Language Tests
A.D. McCarthy, K.P. Yancey, G.T. LaFlair, J. Egbert, M. Liao, and B. SettlesEMNLP Proceedings, 2021 -
Mining Process Data to Detect Aberrant Test Takers
M. Liao, J. Patton, R. Yan, and H. JiaoMeasurement: Interdisciplinary Research and Perspectives, 2021 -
Methods for Language Learning Assessment at Scale: Duolingo Case Study
L. Portnoff, E. Gustafson, J. Rollinson and K. BicknellEDM Proceedings, 2021 -
A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications
K.P. Yancey and B. SettlesKDD Proceedings, 2020 -
Exploring Neural Entity Representations for Semantic Information
A. Runge and E. HovyEMNLP Proceedings, 2020 -
Simultaneous Translation and Paraphrase for Language Education
S. Mayhew, K. Bicknell, C. Brust, B. McDowell, W. Monroe, and B. SettlesACL Proceedings, 2020 • Duolingo Shared Task -
Indigenous Language Teaching Policy in California/the U.S.: What’s Left Unsaid in Discourse/Funding
E.A. MolineIssues in Applied Linguistics, 2020 -
Predictors Of Second Language English Lexical Recognition: Further Insights From A Large Database Of Second Language Lexical Decision Times
S. Skalicky, S.A. Crossley, and C.M. BergerThe Mental Lexicon, 2020 -
Ongoing Cognitive Processing Influences Precise Eye-Movement Targets in Reading
K. Bicknell, R. Levy, and K. RaynerPsychological Science, 2020 -
Machine Learning Driven Language Assessment
B. Settles, G.T. LaFlair, and M. HagiwaraTransactions of the Association for Computational Linguistics, 2020 -
Using LSTMs to Assess the Obligatoriness of Phonological Distinctive Features for Phonotactic Learning
N. Mirea and K. BicknellACL Proceedings, 2019 -
-
A Rational Model of Word Skipping in Reading: Ideal Integration of Visual and Linguistic Information
Y. Duan and K. BicknellCogSci Proceedings, 2019 -
Observing the Emergence of Constructional Knowledge: Verb Patterns in German and Spanish Learners of English at Different Proficiency Levels
U. Römer and C.M. BergerStudies in Second Language Acquisition, 2019 -
Influence of Speaking Style Adaptations and Semantic Context on the Time Course of Word Recognition in Quiet and in Noise
S.V.H. van der Feest, C.P. Blanco, and R. SmiljanicaJournal of Phonetics, 2019 -
Second Language Acquisition Modeling
B. Settles, C. Brust, E. Gustafson, M. Hagiwara and N. MadnaniNAACL-HLT Proceedings, 2018 • Duolingo Shared Task -
Learning Additional Languages As Hierarchical Probabilistic Inference: Insights from First Language Processing
B. Pajak, A.B. Fine, D.F. Kleinschmidt, and T.F. JaegerLanguage Learning, 2016 -
A Trainable Spaced Repetition Model for Language Learning
B. Settles and B. MeederACL Proceedings, 2016 -
Difficulty in Learning Similar-Sounding Words: A Developmental Stage or a General Property of Learning?
B. Pajak, S.C. Creel, and R. LevyJournal of Experimental Psychology, 2016 -
Self-directed Learning Favors Local, Rather Than Global, Uncertainty
D.B. Markant, B. Settles, and T.M. GureckisCognitive Science, 2016 -
Data & Tools
-
2020 Notification Bandit Data
Replication data for our KDD 2020 paper, "A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications." Includes 200 million examples of Duolingo practice reminder push notifications sent to Duolingo users over a 35 day period, including which template was used, whether the user converted within 2 hours, and other metadata.
-
2020 STAPLE Shared Task Data
Data for the 2020 Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE). This corpus contains more than 3 million pairs of English sentences with multiple possible translations into Portuguese, Hungarian, Japanese, Korean, and Vietnamese.
-
2018 SLAM Shared Task Data
Data for the 2018 Shared Task on Second Language Acquisition Modeling (SLAM). This corpus contains 7 million words produced by learners of English, Spanish, and French. It includes user demographics, morph-syntactic metadata, response times, and longitudinal errors for 6k+ users over 30 days.
-
Spaced Repetition Data
Data used to develop our half-life regression (HLR) spaced repetition algorithm. This is a collection of 13 million user-word pairs for learners of several languages with a variety of language backgrounds. It includes practice recall rates, lag times between practices, and other morpho-lexical metadata.
Our Team
We are a diverse team of experts in AI and machine learning, data science, learning sciences, UX research, linguistics, and psychometrics. We work closely with product teams to build innovative features based on world-class research. We are growing, so check out our job openings below!
-
André Horie AI + Machine Learning -
Bożena Pająk Learning + Curriculum -
Erin Gustafson Data Science + Analytics -
Cindy Berger Learning + Curriculum -
Angela DiCostanzo Learning + Curriculum -
Cindy Blanco Learning + Curriculum -
Lisa Bromberg Learning + Curriculum -
Klinton Bicknell AI + Machine Learning -
Will Monroe AI + Machine Learning -
Geoff LaFlair Assessment + Psychometrics -
Hope Wilson Learning + Curriculum -
Kevin Yancey AI + Machine Learning -
Xiangying Jiang Learning + Curriculum -
Jessica Becker Learning + Curriculum -
Stephen Mayhew AI + Machine Learning -
Meredith McDermott UX Research -
Andrew Runge AI + Machine Learning -
Connor Brem AI + Machine Learning -
Emily Moline Learning + Curriculum -
Elizabeth Strong Learning + Curriculum -
Cory Wheeler Learning + Curriculum -
Lauren Bilsky AI + Machine Learning -
Emma Gibson Learning + Curriculum -
James Leow Learning + Curriculum -
Danchen Yang Learning + Curriculum -
Isabel Deibel Learning + Curriculum -
Elizabeth Onstwedder Learning + Curriculum -
Kevin Lenzo AI + Machine Learning -
Mancy Liao Assessment + Psychometrics -
Nora Gordon Learning + Curriculum -
Sharon Wilkinson Learning + Curriculum -
Naveen Shankar Data Science + Analytics -
Antony Kunnan Assessment + Psychometrics -
Jackie Bialostozky Learning + Curriculum -
Lucy Portnoff Data Science + Analytics -
Ramsey Cardwell Assessment + Psychometrics -
Alina von Davier Assessment + Psychometrics -
Yigal Attali Assessment + Psychometrics -
Audrey Kittredge Learning + Curriculum -
Ben Reuveni Learning + Curriculum -
J.R. Lockwood Assessment + Psychometrics -
Rich Forest Learning + Curriculum -
Mark Lock Data Science + Analytics -
Will Belzak Assessment + Psychometrics
Ready to work with us?
-
AI + Machine Learning
Develop ML-driven technologies for novel applications in language, learning, and assessment that are used by millions of people every day.
-
Data Science + Analytics
Support data-driven product decisions and generate insights to guide product development for millions of learners worldwide.
-
Learning + Curriculum
Help improve how millions of people learn languages on Duolingo.
