The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation

Dung Manh Nguyen, Le Hai Nam, Anh T. V. Dau, Anh Minh Nguyen, Khanh Nghiem, Jin L.C. Guo, Nghi D. Q. Bui

Submission Type: Regular Long Paper

Submission Track: Resources and Evaluation

Keywords: deep-learning, ai4code, dataset, benchmark, code-understanding, code-generation

TL;DR: A new dataset for advancing code understanding and code intelligence

Abstract: We present The Vault, an open-source dataset of high quality code-text pairs in multiple programming languages for training large language models to understand and generate code. We propose methods for thoroughly extracting samples that use both rules and deep learning to ensure that they contain high-quality pairs of code and text, resulting in a dataset of 43 million high-quality code-text pairs. We thoroughly evaluated this dataset and discovered that when used to train common code language models (such as CodeT5, CodeBERT, and CodeGen), it outperforms the same models train on other datasets such as CodeSearchNet. These evaluations included common coding tasks such as code generation, code summarization, and code search. The Vault can be used by researchers and practitioners to train a wide range of big language models that understand code. Alternatively, researchers can use our data cleaning methods and scripts to improve their own datasets. We anticipate that using The Vault to train large language models will improve their ability to understand and generate code, propelling AI research and software development forward. We are releasing our source code and a framework to make it easier for others to replicate our results.

Submission Number: 3799