Code Search
49 papers with code • 5 benchmarks • 10 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
These leaderboards are used to track progress in Code Search
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Code Search models and implementationsDatasets
CodeSearchNet
CodeXGLUE
StaQC
XLCoST
ISAdetect dataset
Latest papers
AutoCodeRover: Autonomous Program Improvement
Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding.
ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search
jordane95/procqa
•
•
Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets.
Source Code Clone Detection Using Unsupervised Similarity Measures
jorge-martinez-gil/codesim
•
•
Assessing similarity in source code has gained significant attention in recent years due to its importance in software engineering tasks such as clone detection and code search and recommendation.
TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation
Our framework has several advantages over existing methods: (1) It is flexible and adaptable, because it can easily be extended to other downstream tasks that require code representation (such as code-clone detection and classification); (2) it is efficient and scalable, because it does not require a large model or a large amount of training data, and it can support any programming language; (3) it is not limited to unsupervised learning, but can also be applied to some supervised learning tasks by incorporating task-specific labels or objectives; and (4) it can also adjust the number of encoder parameters based on computing resources.
Language Models are Universal Embedders
As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is desirable to build a unified embedding model rather than dedicated ones for each scenario.
Rethinking Negative Pairs in Code Search
Alex-HaochenLi/Soft-InfoNCE
•
•
In our proposed loss function, we apply three methods to estimate the weights of negative pairs and show that the vanilla InfoNCE loss is a special case of Soft-InfoNCE.
MELT: Mining Effective Lightweight Transformations from Pull Requests
By leveraging code examples mined from the library source and automatically generated code examples based on the pull requests, we infer transformation rules in \comby, a language for structural code search and replace.
Constructing Multilingual Code Search Dataset Using Neural Machine Translation
Code search is a task to find programming codes that semantically match the given natural language queries.
Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data
SANTA proposes two pretraining methods to make language models structure-aware and learn effective representations for structured data: 1) Structured Data Alignment, which utilizes the natural alignment relations between structured data and unstructured data for structure-aware pretraining.
Backdooring Neural Code Search
wssun/badcode
•
•
Neural code search models are hence behind many such engines.
