A Trainable Spaced Repetition Model for Language Learning

Settles, Burr; Meeder, Brendan

doi:10.18653/v1/p16-1174

Cited by 141 publications

(123 citation statements)

References 19 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…Settles and Meeder (2016) and Ridgeway et al (2017) recently proposed non-linear regressions that explicitly encode the rate of forgetting as part of a decision surface, however none of the current teams chose to do this. Instead, forgetting was either modeled through engineered features (e.g., user/token histories), or opaquely handled by sequential RNN architectures.…”

Section: Related Workmentioning

confidence: 99%

Second Language Acquisition Modeling

Settles¹,

Brust²,

Gustafson³

et al. 2018

Proceedings of the Thirteenth Workshop on Innovative Use of NLP For Building Educational Applications

Self Cite

View full text Add to dashboard Cite

We present the task of second language acquisition (SLA) modeling. Given a history of errors made by learners of a second language, the task is to predict errors that they are likely to make at arbitrary points in the future. We describe a large corpus of more than 7M words produced by more than 6k learners of English, Spanish, and French using Duolingo, a popular online language-learning app. Then we report on the results of a shared task challenge aimed studying the SLA task via this corpus, which attracted 15 teams and synthesized work from various fields including cognitive science, linguistics, and machine learning.

show abstract

Section: Related Workmentioning

confidence: 99%

Second Language Acquisition Modeling

Settles¹,

Brust²,

Gustafson³

et al. 2018

Proceedings of the Thirteenth Workshop on Innovative Use of NLP For Building Educational Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…We apply S3D [2] to benchmark datasets from the UCI Machine Learning Repository [18] and Luís Torgo's personal website. [3] In addition, we include five large-scale behavioral datasets, as described in the following paragraphs.…”

Section: Resultsmentioning

confidence: 99%

“…Aside from increasing our understanding of social systems, knowledge about what factors affect behavioral outcomes can also help us design of social platforms that improve human performance, including, for example, optimizing learning on educational platforms [2,34] or fairer judicial decisions [35]. The insights gained from the model can help design effective intervention strategies that change behaviors so as to improve individual and collective well-being.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Predicting and explaining behavioral data with structured feature space decomposition

Fennell¹,

Zuo

Lerman³

2019

EPJ Data Sci.

View full text Add to dashboard Cite

Modeling human behavioral data is challenging due to its scale, sparseness (few observations per individual), heterogeneity (differently behaving individuals), and class imbalance (few observations of the outcome of interest). An additional challenge is learning an interpretable model that not only accurately predicts outcomes, but also identifies important factors associated with a given behavior. To address these challenges, we describe a statistical approach to modeling behavioral data called the structured sum-of-squares decomposition (S3D). The algorithm, which is inspired by decision trees, selects important features that collectively explain the variation of the outcome, quantifies correlations between the features, and partitions the subspace of important features into smaller, more homogeneous blocks that correspond to similarly-behaving subgroups within the population. This partitioned subspace allows us to predict and analyze the behavior of the outcome variable both statistically and visually, giving a medium to examine the effect of various features and to create explainable predictions. We apply S3D to learn models of online activity from large-scale data collected from diverse sites, such as Stack Exchange, Khan Academy, Twitter, Duolingo, and Digg. We show that S3D creates parsimonious models that can predict outcomes in the held-out data at levels comparable to state-of-the-art approaches, but in addition, produces interpretable models that provide insights into behaviors. This is important for informing strategies aimed at changing behavior, designing social systems, but also for explaining predictions, a critical step towards minimizing algorithmic bias.

show abstract

“…Anki, a popular flashcard application incorporates a scheduling algorithm in order to implement spacing effect. More recently we have seen Duolingo, a language learning application implement a machine learning based spacing effect called HalfLife-Regression (Settles and Meeder, 2016). With Testing Effect in place, it would be beneficial to incorporate spacing effect as it has shown great promise in practical applications .…”

Section: Discussion and Future Workmentioning

confidence: 99%