SOTAVerified

Code Search

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.

Source: When Deep Learning Met Code Search

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 125 papers

TitleStatusHype
Text and Code Embeddings by Contrastive Pre-TrainingCode1
AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees—0
Analyzing CodeBERT's Performance on Natural Language Code Search—0
Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning—0
Energy-bounded Learning for Robust Models of Code—0
EDAssistant: Supporting Exploratory Data Analysis in Computational Notebooks with In-Situ Code Search and Recommendation—0
Bridging Pre-trained Models and Downstream Tasks for Source Code UnderstandingCode1
Semantic Code Search for Smart Contracts—0
CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search—0
A New Search Paradigm for Natural Language Code Search—0
GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code SearchCode1
Cascaded Fast and Slow Models for Efficient Semantic Code Search—0
A Systematic Review of Automated Query Reformulations in Source Code Search—0
SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation—0
Distilling Transformers for Neural Cross-Domain Search—0
Bag-of-Words Baselines for Semantic Code Search—0
Is a Single Model Enough? MuCoS: A Multi-Model Ensemble Learning for Semantic Code SearchCode1
Multimodal Representation for Neural Code SearchCode1
Contrastive Learning of Natural Language and Code Representations for Semantic Code Search—0
Memorization and Generalization in Neural Code Intelligence ModelsCode0
Clone-Seeker: Effective Code Clone Search Using Annotations—0
CoDesc: A Large Code-Description Parallel DatasetCode0
CoSQA: 20,000+ Web Queries for Code Search and Question AnsweringCode1
BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?—0
Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers—0
Show:102550
← PrevPage 4 of 5Next →
All datasetsCodeSearchNetCoDescCodeXGLUE - AdvTestCodeSearchNet - RubyCodeXGLUE - WebQueryTestCoIR

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1cpt-code MOverall93.5—Unverified
2cpt-code SOverall93.4—Unverified
3GraphCodeBERTOverall77.4—Unverified
4CodeT5+ 770MOverall77.4—Unverified
5CodeT5+ 220MOverall77.1—Unverified
6CodeBERTOverall76—Unverified
#ModelMetricClaimedVerifiedStatus
1Self-attentionTest MRR0.84—Unverified
2NBOWTest MRR0.81—Unverified
3RNNTest MRR0.77—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeT5+ 770MMRR44.7—Unverified
2CodeT5+ 220MMRR43.3—Unverified
3CodeBERTMRR27.19—Unverified
#ModelMetricClaimedVerifiedStatus
1Uni-SBTMRR0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeBERTAccuracy47.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Voyage-code-002nDCG@1056.26—Unverified