Open AccessProceedings Article
Learning Program Embeddings to Propagate Feedback on Student Code
Chris Piech,Jonathan Huang,Andy Nguyen,Mike Phulsuksombati,Mehran Sahami,Leonidas J. Guibas +5 more
- pp 1093-1102
TLDR
A neural network method is introduced to encode programs as a linear mapping from an embedded precondition space to an embedded postcondition space and an algorithm for feedback at scale is proposed using these linear maps as features.Abstract:
Providing feedback, both assessing final work and giving hints to stuck students, is difficult for open-ended assignments in massive online classes which can range from thousands to millions of students. We introduce a neural network method to encode programs as a linear mapping from an embedded precondition space to an embedded postcondition space and propose an algorithm for feedback at scale using these linear maps as features. We apply our algorithm to assessments from the Code.org Hour of Code and Stanford University's CS1 course, where we propagate human comments on student assignments to orders of magnitude more submissions.read more
Citations
More filters
Book ChapterDOI
Modelling Math Learning on an Open Access Intelligent Tutor
TL;DR: A methodology to analyze large amount of students’ learning states on two math courses offered by Global Freshman Academy program at Arizona State University to examine the potential of the embedding representations on students learning is presented.
Journal ArticleDOI
DPWord2Vec: Better Representation of Design Patterns in Semantics
TL;DR: This study builds a corpus containing more than 400 thousand documents extracted from design pattern books, Wikipedia, and Stack Overflow, and redefine the concept of context window to associate design patterns with words and proposes DPWord2Vec that embeds design patterns and natural language words into vectors simultaneously.
Book ChapterDOI
A Systematic Approach for Analyzing Students’ Computational Modeling Processes in C2STEM
TL;DR: An unsupervised learning method is used to characterize student learning behaviors and how these behaviors relate to learning gains in STEM and CT.
Proceedings ArticleDOI
Making the Most of Repetitive Mistakes: An Investigation into Heuristics for Selecting and Applying Feedback to Programming Coursework
Roger Howell,Shun Ha Sylvia Wong +1 more
TL;DR: Examination of feedback given to coursework submissions to a UK level 5, university-level, data structures and algorithms course is examined to determine heuristics used to trigger particular feedback comments that are common between submissions and cohorts and discusses how the identifiedHeuristics may be used to promote timeliness and consistency of feedback without jeopardising the quality.
Proceedings ArticleDOI
Function Names: Quantifying the Relationship Between Identifiers and Their Functionality to Improve Them
TL;DR: A software system to automate labor-intensive tasks, detect poor function names and recommend replacements, and attempt to learn the relationship between functions in different programs to improve their names is developed.
References
More filters
Proceedings Article
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization.
TL;DR: Adaptive subgradient methods as discussed by the authors dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradient-based learning, which allows us to find needles in haystacks in the form of very predictive but rarely seen features.
Journal Article
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
TL;DR: This work describes and analyze an apparatus for adaptively modifying the proximal function, which significantly simplifies setting a learning rate and results in regret guarantees that are provably as good as the best proximal functions that can be chosen in hindsight.
Journal Article
Random search for hyper-parameter optimization
James Bergstra,Yoshua Bengio +1 more
TL;DR: This paper shows empirically and theoretically that randomly chosen trials are more efficient for hyper-parameter optimization than trials on a grid, and shows that random search is a natural baseline against which to judge progress in the development of adaptive (sequential) hyper- parameter optimization algorithms.
Proceedings Article
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Richard Socher,Alex Perelygin,Jean Y. Wu,Jason Chuang,Christopher D. Manning,Andrew Y. Ng,Christopher Potts +6 more
TL;DR: A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.
Book
A complexity measure
TL;DR: In this paper, a graph-theoretic complexity measure for managing and controlling program complexity is presented. But the complexity is independent of physical size, and complexity depends only on the decision structure of a program.