Corpus ID: 215754320

Code Completion using Neural Attention and Byte Pair Encoding

@article{Arkesteijn2020CodeCU,
  title={Code Completion using Neural Attention and Byte Pair Encoding},
  author={Youri Arkesteijn and Nikhil Saldanha and Bastijn Kostense},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.06343}
}

Youri Arkesteijn, Nikhil Saldanha, Bastijn Kostense

Published 2020

Computer Science

ArXiv

In this paper, we aim to do code completion based on implementing a Neural Network from Li et. al.. Our contribution is that we use an encoding that is in-between character and word encoding called Byte Pair Encoding (BPE). We use this on the source code files treating them as natural text without first going through the abstract syntax tree (AST). We have implemented two models: an attention-enhanced LSTM and a pointer network, where the pointer network was originally introduced to solve out… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed