Papers with Code 아카이브
Code Search
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 6
- 보존된 평가 기록
- 15
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/CGCL-codes/naturalcc
공식 코드What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code
https://github.com/DeepSoftwareAnalytics/CoSQA_Plus
공식 코드CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents
https://github.com/Jun-jie-Huang/CoCLR
공식 코드CoSQA: 20,000+ Web Queries for Code Search and Question Answering
https://github.com/Siddharth-Gandhi/ds
공식 코드https://github.com/Xzh0u/MuCoS
공식 코드Is a Single Model Enough? MuCoS: A Multi-Model Ensemble Learning for Semantic Code Search
https://github.com/alex-haochenli/racs
공식 코드https://github.com/alex-haochenli/reco
공식 코드Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search
https://github.com/aravi11/funcGNN
공식 코드funcGNN: A Graph Neural Network Approach to Program Similarity
https://github.com/coir-team/coir
공식 코드CoIR: A Comprehensive Benchmark for Code Information Retrieval Models
https://github.com/csebuetnlp/CoDesc
공식 코드https://github.com/degraphcs/DeGraphCS
공식 코드deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search
https://github.com/drndr/code_isotropy
공식 코드Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search
https://github.com/drndr/gencodesearchnet
공식 코드https://github.com/evalplus/repoqa
공식 코드https://github.com/facebookresearch/CodeGen/blob/main/docs/dobf.md
공식 코드DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
https://github.com/fsoft-ai4code/thevault
공식 코드The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation
https://github.com/github/CodeSearchNet
공식 코드CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
https://github.com/iamfaith/transformcode
공식 코드TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation
https://github.com/izhx/uni-rep
공식 코드https://github.com/jianguda/mrncs
공식 코드https://github.com/jordane95/procqa
공식 코드ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search
https://github.com/jorge-martinez-gil/codesim
공식 코드Source Code Clone Detection Using Unsupervised Similarity Measures
https://github.com/jorge-martinez-gil/ensemble-codesim
공식 코드Advanced Detection of Source Code Clones via an Ensemble of Unsupervised Similarity Measures
https://github.com/masud99r/code-intent
공식 코드Evaluating How Developers Use General-Purpose Web-Search for Code Retrieval
https://github.com/mdrafiqulrabin/CI-Memorization
공식 코드Memorization and Generalization in Neural Code Intelligence Models
https://github.com/microsoft/CodeBERT
공식 코드CodeBERT: A Pre-Trained Model for Programming and Natural Languages
https://github.com/microsoft/CodeXGLUE
공식 코드CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
https://github.com/microsoft/Search4Code
공식 코드Search4Code: Code Search Intent Classification Using Weak Supervision
https://github.com/microsoft/ar2
공식 코드CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search
https://github.com/mrezende/concra
공식 코드CoNCRA: A Convolutional Neural Network Code Retrieval Approach
https://github.com/nokia/codesearch
공식 코드Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent
https://github.com/nus-apr/auto-code-rover
공식 코드https://github.com/openmatch/openmatch
공식 코드Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data
https://github.com/overwindows/semanticcodesearch
공식 코드Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus
https://github.com/palmtreemodel/palmtree
공식 코드PalmTree: Learning an Assembly Language Model for Instruction Embedding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.