2021

Automatic Code Generation using Pre-Trained Language Models

Perez, Luis, Ottens, Lizi, Viswanathan, Sudharshan

Understand

Recent advancements in natural language processing \cite{gpt2} \cite{BERT} have led to near-human performance in multiple natural language tasks.

  • In this paper, we seek to understand whether similar techniques can be applied to a highly structured environment with strict syntax rules.
  • Specifically, we propose an end-to-end machine learning model for code generation in the Python language built on-top of pre-trained language models.
  • We demonstrate that a fine-tuned model can perform well in code generation tasks, achieving a BLEU score of 0.22, an improvement of 46\% over a reasonable sequence-to-sequence baseline.

Built on

Similar

Then

  • Codesearchnet challenge: Evaluating the state of semantic code search, 2019

    Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, and Marc Brockschmidt · 2019

    Later among the works it cites.

  • Codegru: Context-aware deep learning with gated recurrent unit for source code modeling

    Original

    Yasir Hussain, Zhiqiu Huang, Senzhang Wang, and Yu Zhou · 2019

    Later among the works it cites.

  • Treegen: A tree-based transformer architecture for code generation, 2019

    Zeyu Sun, Qihao Zhu, Yingfei Xiong, Yican Sun, Lili Mou, and Lu Zhang · 2019

    Later among the works it cites.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…