Automatic Code Generation using Pre-Trained Language Models

Abstract

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. All results and related code used for training and data processing are available on GitHub.

arXiv comment9 pages, 11 figures

References in corpus (3)

• CodeGRU: Context-aware Deep Learning with Gated Recurrent Unit for Source Code Modeling
• TreeGen: A Tree-Based Transformer Architecture for Code Generation
• TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks

Cited by in corpus (1)

• On the Effectiveness of Pretrained Models for API Learning