sk_p: a neural program corrector for MOOCs
We present a novel technique for automatic program correction in MOOCs, capable of fixing both syntactic and semantic errors without manual, problem specific correction strategies. Given an incorrect student program, it generates candidate programs from a distribution of likely corrections, and chec...
Main Authors: | Pu, Yewen (Contributor), Narasimhan, Karthik Rajagopal (Contributor), Solar Lezama, Armando (Contributor), Barzilay, Regina (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
Association for Computing Machinery,
2017-07-17T18:05:43Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Verifiable reinforcement learning via policy extraction
by: Solar Lezama, Armando, et al.
Published: (2021) -
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
by: Narasimhan, Karthik Rajagopal, et al.
Published: (2016) -
An unsupervised method for uncovering morphological chains
by: Narasimhan, Karthik Rajagopal, et al.
Published: (2015) -
Learning to acquire information
by: Pu, Yewen, et al.
Published: (2021) -
Skp2 and Skp2B team up against Rb and p53
by: Germain Doris
Published: (2011-01-01)