English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

High-quality computer science education is limited by the difficulty ofproviding instructor feedback to students at scale. While this feedback couldin principle be automated, supervised approaches to predicting the correctfeedback are bottlenecked by the intractability of annotating large quantitiesof student code. In this paper, we instead frame the problem of providingfeedback as few-shot classification, where a meta-learner adapts to givefeedback to student code on a new programming question from just a few examplesannotated by instructors. Because data for meta-training is limited, we proposea number of amendments to the typical few-shot learning framework, includingtask augmentation to create synthetic tasks, and additional side information tobuild stronger priors about each task. These additions are combined with atransformer architecture to embed discrete sequences (e.g. code) to aprototypical representation of a feedback class label. On a suite of few-shotnatural language processing tasks, we match or outperform state-of-the-artperformance. Then, on a collection of student solutions to exam questions froman introductory university course, we show that our approach reaches an averageprecision of 88% on unseen questions, surpassing the 82% precision of teachingassistants. Our approach was successfully deployed to deliver feedback to16,000 student exam-solutions in a programming course offered by a tier 1university. This is, to the best of our knowledge, the first successfuldeployment of a machine learning based feedback to open-ended student code.

ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback