2017

Semantic Code Repair using Neuro-Symbolic Transformation Networks

Devlin, Jacob, Uesato, Jonathan, Singh, Rishabh et al.

Understand

We study the problem of semantic code repair, which can be broadly defined as automatically fixing non-syntactic bugs in source code.

The majority of past work in semantic code repair assumed access to unit tests against which candidate repairs could be validated.
In contrast, the goal here is to develop a strong statistical model to accurately predict both bug locations and exact fixes without access to information about the intended correct behavior of the program.
Achieving such a goal requires a robust contextual repair model, which we train on a large corpus of real-world source code that has been augmented with synthetically injected bugs.

Pylint, 2001
Sylvain Thenault · 2001
Earlier work this paper cites.
A novel co-evolutionary approach to automatic software bug fixing
Andrea Arcuri and Xin Yao · 2008
Earlier work this paper cites.
Automated patching techniques: the fix is in: technical perspective
Mark Harman · 2010
Earlier work this paper cites.
Genprog: A generic method for automatic software repair
C. Le Goues, T. Nguyen, S. Forrest, and W. Weimer · 2012
Earlier work this paper cites.
Pyflakes, 2012
PyCQA · 2012
Earlier work this paper cites.
Automated feedback generation for introductory programming assignments
Rishabh Singh, Sumit Gulwani, and Armando Solar-Lezama · 2013
Earlier work this paper cites.
Neural machine translation by jointly learning to align and translate
Original
Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio · 2014
Earlier work this paper cites.

Code completion with statistical language models
Veselin Raychev, Martin Vechev, and Eran Yahav · 2014
Cited alongside, same era.
Suggesting accurate method and class names
Miltiadis Allamanis, Earl T. Barr, Christian Bird, and Charles A. Sutton · 2015
Cited alongside, same era.
Predicting program properties from big code
Veselin Raychev, Martin Vechev, and Andreas Krause · 2015
Cited alongside, same era.
A convolutional attention network for extreme summarization of source code
Miltiadis Allamanis, Hao Peng, and Charles A. Sutton · 2016
Cited alongside, same era.
Neural module networks
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, and Dan Klein · 2016
Cited alongside, same era.
Automated correction for syntax errors in programming assignments using recurrent neural networks
Original
Sahil Bhatia and Rishabh Singh · 2016
Cited alongside, same era.
Learning python code suggestion with a sparse pointer network
Original
Avishkar Bhoopchand, Tim Rocktäschel, Earl Barr, and Sebastian Riedel · 2016
Cited alongside, same era.

Learning to superoptimize programs
Original
Rudy Bunel, Alban Desmaison, M Pawan Kumar, Philip HS Torr, and Pushmeet Kohli · 2016
Later among the works it cites.
Cuni system for wmt16 automatic post-editing and multimodal translation tasks
Original
Jindřich Libovickỳ, Jindřich Helcl, Marek Tlustỳ, Pavel Pecina, and Ondřej Bojar · 2016
Later among the works it cites.
Automatic patch generation by learning correct code
Fan Long and Martin Rinard · 2016
Later among the works it cites.
Learning from large codebases
Veselin Raychev · 2016
Later among the works it cites.
Sentence-level grammatical error identification as sequence-to-sequence correction
Original
Allen Schmaltz, Yoon Kim, Alexander M Rush, and Stuart M Shieber · 2016
Later among the works it cites.
Deepfix: Fixing common c language errors by deep learning
Rahul Gupta, Soham Pal, Aditya Kanade, and Shirish Shevade · 2017
Closest in time.

alphaXiv searches the wider corpus for related work and actual follow-ups.

alphaXiv is searching for related work…

Reading the bibliography…