AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference

Mike Wu, Milan Mosse, Noah Goodman, Chris Piech

AAAI 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Robust fine-tuning of zero-shot models · 46 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use rubric sampling to train with synthetic labeled programsCode feedback prediction · P1 bodyF1: +0.31Improved
Use rubric sampling to train with synthetic labeled programsCode feedback prediction · P1 tailF1: +0.13Improved
Combine rubric sampling with an MVAERubric sampling code feedback model · P1 and P8F1: an additional 0.2Improved
Use a novice-authored rubric instead of an expert-authored rubric (ablation)Rubric sampling · P1F1: 0.69 ± 0.03 -> 0.63 ± 0.01Hurt
Use hand-picked PCFG probabilities instead of random probabilities (ablation)Rubric sampling · P1F1: 0.26 ± 0.002 increaseImproved
Learn PCFG probabilities with evolutionary strategies from random initialization (ablation)Rubric sampling · P1F1 difference from hand-picked probabilities: 0.007 ± 0.005Improved
Learn PCFG probabilities with evolutionary strategies (ablation)Rubric sampling · P8F1 relative to expert parameters: 0.005 ± 0.009Improved
Train the MVAE using unlabeled student programs as well as synthetic labeled programs (ablation)Rubric sampling with MVAE · Code.org student-program distributiondistribution matchImproved
Use raw frequency counts instead of the log-Zipf transformation (ablation)MVAE program generation · Code.org student programscoverage of program frequency distributionHurt
Use hand-designed PCFG synthetic data alone instead of the MVAE trained with unlabeled data (ablation)Synthetic student-program generation · Code.org student-program distributiondistribution matchHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy