Corpus ID: 2723946

A Convolutional Attention Network for Extreme Summarization of Source Code

@article{Allamanis2016ACA,
  title={A Convolutional Attention Network for Extreme Summarization of Source Code},
  author={Miltiadis Allamanis and Hao Peng and Charles Sutton},
  journal={ArXiv},
  year={2016},
  volume={abs/1602.03001}
}
Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the model's attention, but previous attentional architectures are not constructed to learn such features specifically. We introduce an attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical… Expand
277 Citations
Source Code Summarization Using Attention-Based Keyword Memory Networks
  • Highly Influenced
Query Attention GloVe GloVe CNN Attention Flow Layer Modeling Layer Output Layer
  • PDF
Improving Automatic Source Code Summarization via Deep Reinforcement Learning
  • Yao Wan, Zhou Zhao, +4 authors Philip S. Yu
  • Computer Science
  • 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE)
  • 2018
  • 79
  • PDF
Guided Attention for Neural Language Models
Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks
  • PDF
Fret: Functional Reinforced Transformer With BERT for Code Summarization
  • 1
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 57 REFERENCES
A Convolutional Neural Network for Modelling Sentences
  • 2,580
  • PDF
A Neural Attention Model for Abstractive Sentence Summarization
  • 1,707
  • PDF
Convolutional Neural Networks over Tree Structures for Programming Language Processing
  • 269
  • PDF
Pointer Networks
  • 1,206
  • PDF
Neural Programmer: Inducing Latent Programs with Gradient Descent
  • 234
  • PDF
Suggesting accurate method and class names
  • 253
  • PDF
Learning to Execute
  • 407
  • PDF
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
  • 5,825
  • PDF
A unified architecture for natural language processing: deep neural networks with multitask learning
  • 4,334
  • PDF
...
1
2
3
4
5
...