src-d / reading-club

Paper reading club at source{d}
Creative Commons Attribution Share Alike 4.0 International
115 stars 12 forks source link

Next paper candidates: 13 Dec #98

Closed m09 closed 4 years ago

m09 commented 4 years ago

Next paper candidates

Let's propose papers to study next! All papers mentioned in the comments of this issue will be listed in the next vote.

m09 commented 4 years ago

Last session runner-up: Learning to Fix Build Errors with Graph2Diff Neural Networks

Professional software developers spend a significant amount of time fixing builds, but this has received little attention as a problem in automatic program repair. We present a new deep learning architecture, called Graph2Diff, for automatically localizing and fixing build errors. We represent source code, build configuration files, and compiler diagnostic messages as a graph, and then use a Graph Neural Network model to predict a diff. A diff specifies how to modify the code's abstract syntax tree, represented in the neural network as a sequence of tokens and of pointers to code locations. Our network is an instance of a more general abstraction that we call Graph2Tocopo, which is potentially useful in any development tool for predicting source code changes. We evaluate the model on a dataset of over 500k real build errors and their resolutions from professional developers. Compared to the approach of DeepDelta (Mesbah et al., 2019), our approach tackles the harder task of predicting a more precise diff but still achieves over double the accuracy.