Corpus ID: 220041905

Corrigendum and Supplement to "Improve Language Modelling for Code Completion through Learning General Token Repetition of Source Code (with Optimized Memory)"

@article{Yang2020CorrigendumAS,
  title={Corrigendum and Supplement to "Improve Language Modelling for Code Completion through Learning General Token Repetition of Source Code (with Optimized Memory)"},
  author={Yixiao Yang},
  journal={arXiv: Software Engineering},
  year={2020}
}
  • Yixiao Yang
  • Published 2020
  • Computer Science
  • arXiv: Software Engineering
This paper is written because I receive several inquiry emails saying it is hard to achieve good results when applying token repetition learning techniques. If REP (proposed by me) or Pointer-Mixture (proposed by Jian Li) is directly applied to source code to decide all token repetitions, the model performance will decrease sharply. As we use pre-order traversal to traverse the Abstract Syntax Tree (AST) to generate token sequence, tokens corresponding to AST grammar are ignored when learning… Expand

References

SHOWING 1-10 OF 18 REFERENCES
Improve Language Modelling for Code Completion through Learning General Token Repetition of Source Code
  • 4
A statistical semantic language model for source code
  • 159
Code Completion with Neural Attention and Pointer Networks
  • 59
  • PDF
Code completion with statistical language models
  • 389
  • PDF
On the localness of software
  • 154
  • PDF
Statistical Learning of API Fully Qualified Names in Code Snippets of Online Forums
  • 19
Improve Language Modeling for Code Completion Through Learning General Token Repetition of Source Code with Optimized Memory
  • 3
  • Highly Influential
Graph-Based Statistical Language Model for Code
  • A. Nguyen, T. Nguyen
  • Computer Science
  • 2015 IEEE/ACM 37th IEEE International Conference on Software Engineering
  • 2015
  • 124
  • PDF
Toward Deep Learning Software Repositories
  • 194
  • PDF
...
1
2
...