A challenge in designing high-stakes language assessments is calibrating the test item difficulties, either a priori or from limited pilot test data. While prior work has addressed ‘cold start’ estimation of item difficulties without piloting, we devise a multi-task generalized linear model with BERT features to jump-start these estimates, rapidly improving their quality with as few as 500 test-takers and a small sample of item exposures (≈6 each) from a large item bank (≈4,000 items). Our joint model provides a principled way to compare test-taker proficiency, item difficulty, and language proficiency frameworks like the Common European Framework of Reference (CEFR). This also enables new item difficulty estimates without piloting them first, which in turn limits item exposure and thus enhances test item security. Finally, using operational data from the Duolingo English Test, a high-stakes English proficiency test, we find that the difficulty estimates derived using this method correlate strongly with lexico-grammatical features that correlate with reading complexity.
We describe a method for rapidly creating language proficiency assessments, and provide experimental evidence that such tests can be valid, reliable, and secure. Our approach is the first to use machine learning and natural language processing to induce proficiency scales based on a given standard, and then use linguistic models to estimate item difficulty directly for computer-adaptive testing. This alleviates the need for expensive pilot testing with human subjects. We used these methods to develop an online proficiency exam called the Duolingo English Test, and demonstrate that its scores align significantly with other high-stakes English assessments. Furthermore, our approach produces test scores that are highly reliable, while generating item banks large enough to satisfy security requirements.
We present the task of Simultaneous Translation and Paraphrasing for Language Education (STAPLE). Given a prompt in one language, the goal is to generate a diverse set of correct translations that language learners are likely to produce. This is motivated by the need to create and maintain large, high-quality sets of acceptable translations for exercises in a language-learning application, and synthesizes work spanning machine translation, MT evaluation, automatic paraphrasing, and language education technology. We developed a novel corpus with unique properties for five languages (Hungarian, Japanese, Korean, Portuguese, and Vietnamese), and report on the results of a shared task challenge which attracted 20 teams to solve the task. In our meta-analysis, we focus on three aspects of the resulting systems: external training corpus selection, model architecture and training decisions, and decoding and filtering strategies. We find that strong systems start with a large amount of generic training data, and then fine-tune with in-domain data, sampled according to our provided learner response frequencies.
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.