A Trainable Spaced Repetition Model for Language Learning

By Burr Settles, Brendan Meeder. 2016

219 citations recorded by the source corpus.

We present half-life regression (HLR) , a novel model for spaced repetition practice with applications to second language acquisition. HLR combines psycholinguistic theory with modern machine learning techniques, indirectly estimating the “half-life” of a word or concept in a student’s long-term memory. We use data from Duolingo — a popular online language learning application — to ﬁt HLR models, reducing error by 45%+ compared to several baselines at predicting student recall rates. HLR model weights also shed light on which linguistic concepts are systematically challenging for second language learners. Finally, HLR was able to improve Duolingo daily student engagement by 12% in an operational user study.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Using Simpson's Paradox to Discover Interesting Patterns in Behavioral Data (2018, methodology): “The DL halflife-regression (Settles and Meeder 2016) dataset (https://github.”
Teaching Multiple Concepts to Forgetful Learners (2018, methodology): “Settles and Meeder (2016) [14] introduced Half-life Regression (HLR) as a generalization of these heuristics, and showed that HLR in general outperforms the existing approaches.”
An Overview of Machine Teaching (2018, background): “One concrete learning task that has gained a lot of recent interest is that of reviewing content via flashcards (e.g. for teaching vocabulary of a foreign language in Duolingo) [35].”
Knowledge Tracing: A Survey (2022, methodology): “Diferent from the previous traditional KT models that use forgetting features only with regard to questions with the same KC [56, 91, 94, 102], this work considers a student’s interactions in the whole sequence so as to model more complex forgetting behavior.”
Teaching Multiple Concepts to a Forgetful Learner (2018, methodology): “We defer the details of our sensitivity study of the HLR parameters to the supplemental materials.”