CodeSearchNet Challenge: Evaluating the State of Semantic Code Search

TL;DR

This paper introduces the CodeSearchNet Challenge, a large-scale benchmark for evaluating semantic code search methods across multiple programming languages, aiming to advance research in bridging natural language and code retrieval.

Contribution

It provides a comprehensive dataset, evaluation methodology, and baseline solutions for semantic code search, fostering progress through a public challenge and leaderboard.

Findings

Created a dataset with 6 million functions across 6 languages

Annotated 99 natural language queries with expert relevance labels

Launched a benchmark and baseline solutions for the task

Abstract

Semantic code search is the task of retrieving relevant code given a natural language query. While related to other information retrieval tasks, it requires bridging the gap between the language used in code (often abbreviated and highly technical) and natural language more suitable to describe vague concepts and ideas. To enable evaluation of progress on code search, we are releasing the CodeSearchNet Corpus and are presenting the CodeSearchNet Challenge, which consists of 99 natural language queries with about 4k expert relevance annotations of likely results from CodeSearchNet Corpus. The corpus contains about 6 million functions from open-source code spanning six programming languages (Go, Java, JavaScript, PHP, Python, and Ruby). The CodeSearchNet Corpus also contains automatically generated query-like natural language for 2 million functions, obtained from mechanically scraping and preprocessing associated function documentation. In this article, we describe the methodology used to obtain the corpus and expert labels, as well as a number of simple baseline solutions for the task. We hope that CodeSearchNet Challenge encourages researchers and practitioners to study this interesting task further and will host a competition and leaderboard to track the progress on the challenge. We are also keen on extending CodeSearchNet Challenge to more queries and programming languages in the future.