HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Code Generation On Django

평가 지표

Accuracy

BLEU Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	BLEU Score	Paper Title	Repository
LUKEMarian	78.50	89.34	Leveraging pre-trained language models for code generation	-
Reranker	80.2	-	Reranking for Neural Semantic Parsing	-
MarianCG	81.83	90.41	MarianCG: a code generation transformer model inspired by machine translation	-
lpn (Ling et al., 2016)	62.3	77.6	Latent Predictor Networks for Code Generation
RoBERTaMarian	77.95	88.91	Leveraging pre-trained language models for code generation	-
Tranx	73.7	-	TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
BERTMarian	76.68	56.55	Leveraging pre-trained language models for code generation	-
BERT + TAE	81.03	-	Code Generation from Natural Language with Less Prior and More Monolingual Data
TranX + BERT w/mined	81.03	79.86	The impact of lexical and grammatical processing on generating code from natural language
Phrasal Statistical MT (Ling et al., 2016)	31.5	47.6	Latent Predictor Networks for Code Generation
ELECTRAMarian	65.32	53.02	Leveraging pre-trained language models for code generation	-

0 of 11 row(s) selected.