Code Search
18 papers with code • 5 benchmarks • 9 datasets
The goal of Code Search is to retrieve code fragments from a large code corpus that most closely match a developer’s intent, which is expressed in natural language.
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
Datasets
CodeSearchNet
CodeXGLUE
StaQC
ISAdetect dataset
Greatest papers with code
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
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.
GraphCodeBERT: Pre-training Code Representations with Data Flow
microsoft/CodeBERT
•
•
ICLR 2021
Instead of taking syntactic-level structure of code like abstract syntax tree (AST), we use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables.
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
microsoft/CodeBERT
•
•
Findings of the Association for Computational Linguistics 2020
Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks.
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Benchmark datasets have a significant impact on accelerating research in programming language tasks.
Ranked #1 on
Cloze Test
on CodeXGLUE - CT-maxmin
Faster Person Re-Identification
wangguanan/light-reid
•
•
ECCV 2020
In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better accuracy.
DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks.
When Deep Learning Met Code Search
Our evaluation shows that: 1. adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much; 2. simple networks for supervision can be more effective that more sophisticated sequence-based networks for code search; 3. while it is common to use docstrings to carry out supervision, there is a sizeable gap between the effectiveness of docstrings and a more query-appropriate supervision corpus.
A Toolkit for Generating Code Knowledge Graphs
We make the toolkit to build such graphs as well as the sample extraction of the 2 billion triples graph publicly available to the community for use.
Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent
In this work, we propose and study annotated code search: the retrieval of code snippets paired with brief descriptions of their intent using natural language queries.
Ranked #1 on
Annotated Code Search
on PACS-StaQC-py
CoSQA: 20,000+ Web Queries for Code Search and Question Answering
Jun-jie-Huang/CoCLR
•
•
ACL 2021
Finding codes given natural language query isb eneficial to the productivity of software developers.