preprint · arXiv (Cornell University) · 2016

A Convolutional Attention Network for Extreme Summarization of Source\n Code

Miltiadis Allamanis, Hao Peng, Charles Sutton

Cited by 323Open access

Abstract

Attention mechanisms in neural networks have proved useful for problems in\nwhich the input and output do not have fixed dimension. Often there exist\nfeatures that are locally translation invariant and would be valuable for\ndirecting the model's attention, but previous attentional architectures are not\nconstructed to learn such features specifically. We introduce an attentional\nneural network that employs convolution on the input tokens to detect local\ntime-invariant and long-range topical attention features in a context-dependent\nway. We apply this architecture to the problem of extreme summarization of\nsource code snippets into short, descriptive function name-like summaries.\nUsing those features, the model sequentially generates a summary by\nmarginalizing over two attention mechanisms: one that predicts the next summary\ntoken based on the attention weights of the input tokens and another that is\nable to copy a code token as-is directly into the summary. We demonstrate our\nconvolutional attention neural network's performance on 10 popular Java\nprojects showing that it achieves better performance compared to previous\nattentional mechanisms.\n

Cite this paper

APA 7

Allamanis, M., Peng, H., & Sutton, C. (2016). A Convolutional Attention Network for Extreme Summarization of Source\n Code. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1602.03001

MLA 9

Allamanis, Miltiadis, et al. “A Convolutional Attention Network for Extreme Summarization of Source\n Code.” arXiv (Cornell University), 2016, https://doi.org/10.48550/arxiv.1602.03001.

Chicago

Allamanis, Miltiadis, Hao Peng, and Charles Sutton. 2016. “A Convolutional Attention Network for Extreme Summarization of Source\n Code.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1602.03001.

Harvard

Allamanis, M., Peng, H. and Sutton, C. (2016) ‘A Convolutional Attention Network for Extreme Summarization of Source\n Code’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.1602.03001.

BibTeX

@misc{allamanis2016convolutional,
  title = {{A Convolutional Attention Network for Extreme Summarization of Source\n Code}},
  author = {Allamanis, Miltiadis and Peng, Hao and Sutton, Charles},
  journal = {arXiv (Cornell University)},
  year = {2016},
  doi = {10.48550/arxiv.1602.03001}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.