Relevance Transformer: Generating Concise Code Snippets with Relevance Feedback

Abstract

Tools capable of automatic code generation have the potential to augment programmer's capabilities. While straightforward code retrieval is incorporated into many IDEs, an emerging area is explicit code generation. Code generation is currently approached as a Machine Translation task, with Recurrent Neural Network (RNN) based encoder-decoder architectures trained on code-description pairs. In this work we introduce and study modern Transformer architectures for this task. We further propose a new model called the Relevance Transformer that incorporates external knowledge using pseudo-relevance feedback. The Relevance Transformer biases the decoding process to be similar to existing retrieved code while enforcing diversity. We perform experiments on multiple standard benchmark datasets for code generation including Django, Hearthstone, and CoNaLa. The results show improvements over state-of-the-art methods based on BLEU evaluation. The Relevance Transformer model shows the potential of Transformer-based architectures for code generation and introduces a method of incorporating pseudo-relevance feedback during inference.

References in corpus (7)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Get To The Point: Summarization with Pointer-Generator Networks
• Latent Predictor Networks for Code Generation
• A Retrieve-and-Edit Framework for Predicting Structured Outputs
• Guiding Neural Machine Translation with Retrieved Translation Pieces
• Retrieval-Based Neural Code Generation

Cited by in corpus (5)

• EVIL: Exploiting Software via Natural Language
• Can We Generate Shellcodes via Natural Language? An Empirical Study
• Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation
• PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer
• Neural Program Generation Modulo Static Analysis