AugmentedCode: Examining the Effects of Natural Language Resources in Code Retrieval Models

TL;DR

This paper introduces AugmentedCode, a novel code retrieval approach that enhances performance by leveraging existing code information to create augmented programming language, significantly improving retrieval accuracy on benchmark datasets.

Contribution

The paper presents a new augmented code retrieval framework that outperforms existing models like CodeSearchNet and CodeBERT by utilizing augmented programming language techniques.

Findings

Achieved higher MRR scores of 0.73 and 0.96 on CodeSearchNet and CodeBERT.

Demonstrated the effectiveness of augmented programming language in code retrieval.

Published the improved model on HuggingFace with a demonstration video.

Abstract

Code retrieval is allowing software engineers to search codes through a natural language query, which relies on both natural language processing and software engineering techniques. There have been several attempts on code retrieval from searching snippet codes to function codes. In this paper, we introduce Augmented Code (AugmentedCode) retrieval which takes advantage of existing information within the code and constructs augmented programming language to improve the code retrieval models' performance. We curated a large corpus of Python and showcased the the framework and the results of augmented programming language which outperforms on CodeSearchNet and CodeBERT with a Mean Reciprocal Rank (MRR) of 0.73 and 0.96, respectively. The outperformed fine-tuned augmented code retrieval model is published in HuggingFace at https://huggingface.co/Fujitsu/AugCode and a demonstration video is available at: https://youtu.be/mnZrUTANjGs .