• Corpus ID: 3550454

Learning to Represent Student Knowledge on Programming Exercises Using Deep Learning

@inproceedings{Wang2017LearningTR,
  title={Learning to Represent Student Knowledge on Programming Exercises Using Deep Learning},
  author={L. Wang and Angela Sy and Larry Liu and Chris Piech},
  booktitle={EDM},
  year={2017}
}
Modeling student knowledge while students are acquiring new concepts is a crucial stepping stone towards providing personalized automated feedback at scale. We believe that rich information about a student’s learning is captured within her responses to open-ended problems with unbounded solution spaces, such as programming exercises. In addition, sequential snapshots of a student’s progress while she is solving a single exercise can provide valuable insights into her learning behavior. Creating… 

Figures and Tables from this paper

Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
TLDR
A human-in-the-loop "rubric sampling" approach to tackle the "zero shot" feedback challenge is introduced and is able to provide autonomous feedback for the first students working on an introductory programming assignment with accuracy that substantially outperforms data-hungry algorithms and approaches human level fidelity.
Modeling Knowledge Acquisition from Multiple Learning Resource Types
TLDR
A student knowledge model that can capture knowledge growth as a result of learning from a diverse set of learning resource types while unveiling the association between the learning materials of different types is proposed.
Addressing two problems in deep knowledge tracing via prediction-consistent regularization
TLDR
This work introduces regularization terms that correspond to reconstruction and waviness to the loss function of the original DKT model to enhance the consistency in prediction and alleviates two major problems in the model.
Analyzing student learning trajectories in an introductory programming MOOC
TLDR
This work investigates student learning trajectories on the individual problem level in an MITx MOOC teaching introductory programming in Python, considering simple features of the student and problem as well as more complex keyword occurrence trajectory features associated with student code submissions.
ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
TLDR
This paper proposes a number of amendments to the typical few-shot learning framework, including task augmentation to create synthetic tasks, and additional side information to build stronger priors about each task, which was successfully deployed to deliver feedback to 16,000 student exam-solutions in a programming course offered by a tier 1 university.
Knowledge Tracing Within Single Programming Practice Using Problem-Solving Process Data
TLDR
Two knowledge tracing models that can exploit the problem-solving process data generated by learners from a single programming task are proposed that were competitive with four state-of-the-art models on multiple metrics, including the precision-recall curve, accuracy, specificity, and Cohen's Kappa.
Generative Grading: Neural Approximate Parsing for Automated Student Feedback
TLDR
This paper presents Generative Grading with Neural Approximate Parsing (GG-NAP), a novel computational approach for providing feedback at scale that is capable of both accurately grading student work while also providing verifiability--a property where the model is able to substantiate its claims with a provable certificate.
Deep learning goes to school: toward a relational understanding of AI in education
TLDR
This approach draws attention to relations between various (problematic) units of analysis: flawed data, partially incomprehensible computational methods, narrow forms of educational’ knowledge baked into the online environments, and a reductionist discourse of data science with evident economic ramifications.
Knowing When and Where : Temporal-ASTNN for Student Learning Progression in Novice Programming Tasks
TLDR
This work combines a novel neural network model based on abstract syntactic trees (AST), named ASTNN, and Long-Short Term Memory (LSTM) model, named Temporal-ASTNN for modeling student learning progression in open-ended programming domains.
Learning Cognitive Models Using Neural Networks
TLDR
CogRL is proposed, a novel framework to learn accurate cognitive models in ill-structured domains with no data and little to no human knowledge engineering, and representations learnt using CogRL can be used for accurate automatic cognitive model discovery without using any student performance data.
...
...

References

SHOWING 1-10 OF 28 REFERENCES
Deep Knowledge Tracing
TLDR
The utility of using Recurrent Neural Networks to model student learning and the learned model can be used for intelligent curriculum design and allows straightforward interpretation and discovery of structure in student tasks are explored.
Autonomously Generating Hints by Inferring Problem Solving Policies
TLDR
This paper autonomously generate hints for the Code.org `Hour of Code,' (which is to the best of the authors' knowledge the largest online course to date) using historical student data, and discovers that this statistic is highly predictive of a student's future success.
Knowledge tracing: Modeling the acquisition of procedural knowledge
TLDR
An effort to model students' changing knowledge state during skill acquisition and a series of studies is reviewed that examine the empirical validity of knowledge tracing and has led to modifications in the process.
Learning Program Embeddings to Propagate Feedback on Student Code
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.
Back to the basics: Bayesian extensions of IRT outperform neural networks for proficiency estimation
TLDR
It is found that IRT-based methods consistently matched or outperformed DKT across all data sets at the finest level of content granularity that was tractable for them to be trained on.
Modeling Individualization in a Bayesian Networks Implementation of Knowledge Tracing
TLDR
An elegant way of formulating the individualization problem entirely within a Bayesian networks framework that fits individualized as well as skill specific parameters simultaneously, in a single step is introduced.
Individualized Bayesian Knowledge Tracing Models
TLDR
It is shown that student-specific parameters lead to a tangible improvement when predicting the data of unseen students, and that parameterizing students’ speed of learning is more beneficial than parameterizing a priori knowledge.
Automated feedback generation for introductory programming assignments
TLDR
A simple language for describing error models in terms of correction rules is introduced, and a rule-directed translation strategy is formally defined that reduces the problem of finding minimal corrections in an incorrect program to the problems of synthesizing a correct program from a sketch.
Representation Learning: A Review and New Perspectives
TLDR
Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.
Long Short-Term Memory
TLDR
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
...
...