Fetching the paper…

Reading the bibliography…

2016

A deep language model for software code

Dam, Hoa Khanh, Tran, Truyen, Pham, Trang

Original
PDF
Post on X

Understand

Existing language models such as n-grams for software code often fail to capture a long context where dependent code elements scatter far apart.

In this paper, we propose a novel approach to build a language model for software code to address this particular issue.
Our language model, partly inspired by human memory, is built upon the powerful deep learning-based Long Short Term Memory architecture that is capable of learning long-term dependencies which occur frequently in software code.
Results from our intrinsic evaluation on a corpus of Java projects have demonstrated the effectiveness of our language model.

A deep language model for software code · Around

Built on

Long short-term memory
S. Hochreiter and J. Schmidhuber · 1997
Earlier work this paper cites.
A study of the uniqueness of source code
M. Gabel and Z. Su · 2010
Earlier work this paper cites.
Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics
M. U. Gutmann and A. Hyvärinen · 2012
Earlier work this paper cites.
On the naturalness of software
A. Hindle, E. T. Barr, Z. Su, M. Gabel, and P. Devanbu · 2012
Earlier work this paper cites.

Similar

Advances in optimizing recurrent networks
Y. Bengio, N. Boulanger-Lewandowski, and R. Pascanu · 2013
Cited alongside, same era.
A statistical semantic language model for source code
T. T. Nguyen, A. T. Nguyen, H. A. Nguyen, and T. N. Nguyen · 2013
Cited alongside, same era.
Dropout: A simple way to prevent neural networks from overfitting
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov · 2014
Cited alongside, same era.
On the localness of software
Z. Tu, Z. Su, and P. Devanbu · 2014
Cited alongside, same era.

Then

Recurrent neural network language model training with noise contrastive estimation for speech recognition
X. Chen, X. Liu, M. J. Gales, and P. C. Woodland · 2015
Later among the works it cites.
Toward deep learning software repositories
Original
M. White, C. Vendome, M. Linares-Vásquez, and D. Poshyvanyk · 2015
Later among the works it cites.
DeepSoft: A vision for a deep model of software
H. K. Dam, T. Tran, J. Grundy, and A. Ghose · 2016
Closest in time.
Convolutional neural networks over tree structures for programming language processing
L. Mou, G. Li, L. Zhang, T. Wang, and Z. Jin · 2016
Closest in time.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…