Papers with Code 아카이브
Source Code Summarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 9
- 보존된 평가 기록
- 11
Code Summarization is a task that tries to comprehend code and automatically generate descriptions directly from the source code.
Source: Improving Automatic Source Code Summarization via Deep Reinforcement Learning
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks
PSIMiner: A Tool for Mining Rich Abstract Syntax Trees from Code
Project-Level Encoding for Neural Source Code Summarization of Subroutines
Language-Agnostic Representation Learning of Source Code from Structure and Context
Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach
Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting
Unified Pre-training for Program Understanding and Generation
Universal Representation for Code
Neural Code Summarization
WheaCha: A Method for Explaining the Predictions of Models of Code
Code Summarization with Structure-induced Transformer
InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees
GraphCodeBERT: Pre-training Code Representations with Data Flow
Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations
Towards Demystifying Dimensions of Source Code Embeddings
On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations
Contrastive Code Representation Learning
Retrieval-Augmented Generation for Code Summarization via Hybrid GNN
Learning Semantic Program Embeddings with Graph Interval Neural Network
A Transformer-based Approach for Source Code Summarization
Evaluation of Generalizability of Neural Program Analyzers under Semantic-Preserving Transformations
Improved Code Summarization via a Graph Neural Network
Embedding Java Classes with code2vec: Improvements from Variable Obfuscation
Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning
Code Generation as a Dual Task of Code Summarization
Testing Neural Program Analyzers
Learning Blended, Precise Semantic Program Embeddings
Automatic Source Code Summarization with Extended Tree-LSTM
Recommendations for Datasets for Source Code Summarization
A Convolutional Neural Network for Language-Agnostic Source Code Summarization
Improving Automatic Source Code Summarization via Deep Reinforcement Learning
Structured Neural Summarization
code2seq: Generating Sequences from Structured Representations of Code
Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.