Papers with Code 아카이브
Code Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 28
- 보존된 평가 기록
- 241
Code Generation is an important field to predict explicit code or program structure from multimodal data sources such as incomplete code, programs in another programming language, natural language descriptions or execution examples. Code Generation tools can assist the development of automatic programming tools to improve programming productivity.
Source: Deep Learning for Source Code Modeling and Generation
Image source: Measuring Coding Challenge Competence With APPS
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yangyucheng000/University/tree/main/model-3/starcoder2
EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization
https://github.com/ymcui/chinese-mixtral
https://github.com/young-geng/easylm
https://github.com/yuanmu97/secure-transformer-inference
https://github.com/yueyuel/programgen-lms-reliability
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
https://github.com/yuxiang2/CoNaLa
TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
https://github.com/yuxiaw/openfactcheck
https://github.com/zach-zhiling-zheng/reticular_chemist
https://github.com/zfj1998/CodeBert-Code2Text
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
https://github.com/zhangzwwww/dietcode
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
https://github.com/zhangzwwww/dietcodebert
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
https://github.com/zhaoolee/garss
https://github.com/zihanzhaosjtu/librisqa
https://github.com/zimengq/PyTorch-ReCode
A Syntactic Neural Model for General-Purpose Code Generation
https://github.com/zkcpku/self-edit
https://github.com/zurichnlp/contradecode
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.