SOTAVerified

Source Code Summarization

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 58 papers

TitleStatusHype
Statement-based Memory for Neural Source Code SummarizationCode0
Tram: A Token-level Retrieval-augmented Mechanism for Source Code SummarizationCode0
Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarization—0
An Extractive-and-Abstractive Framework for Source Code SummarizationCode0
Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization—0
Compositionality-Aware Graph2Seq LearningCode0
Meta Learning for Code Summarization—0
Leveraging Unsupervised Learning to Summarize APIs Discussed in Stack OverflowCode0
Meta Learning for Code Summarization—0
Modeling Hierarchical Syntax Structure with Triplet Position for Source Code SummarizationCode0
Retrieval-based Layer-wise Adaptive Transformer for Source Code Summarization—0
Learning Sequential and Structural Information for Source Code Summarization—0
Code to Comment Translation: A Comparative Study on Model Effectiveness & ErrorsCode0
CoDesc: A Large Code-Description Parallel DatasetCode0
Code Structure Guided Transformer for Source Code Summarization—0
HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter NotebooksCode0
Project-Level Encoding for Neural Source Code Summarization of SubroutinesCode0
Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach—0
Neural Code SummarizationCode0
WheaCha: A Method for Explaining the Predictions of Models of Code—0
GN-Transformer: Fusing AST and Source Code information in Graph Networks—0
Automatic Source Code Summarization via Reinforcement Learning—0
GraphCodeBERT: Pre-training Code Representations with Data FlowCode0
Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations—0
A Structural Transformer with Relative Positions in Trees for Code-to-Sequence Tasks—0
Show:102550
← PrevPage 2 of 3Next →
All datasetsDeepCom-JavaParallelCorpus-PythonCoDescCodeSearchNetCodeSearchNet - PythonJava scriptsSummarizing Source Code using a Neural Attention Model - C#Summarizing Source Code using a Neural Attention Model - PythonSummarizing Source Code using a Neural Attention Model - SQL

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AdaMo-noiseBLEU-445.35—Unverified
2AdaMo-basicBLEU-445.3—Unverified
#ModelMetricClaimedVerifiedStatus
1AdaMo-noiseBLEU-434.05—Unverified
2AdaMo-basicBLEU-433.85—Unverified
#ModelMetricClaimedVerifiedStatus
1TransformerBLEU-445.89—Unverified
#ModelMetricClaimedVerifiedStatus
1ContraCodeF117.24—Unverified
#ModelMetricClaimedVerifiedStatus
1AdaMo-basicBLEU-416.46—Unverified
#ModelMetricClaimedVerifiedStatus
1AdaMo-basicBLEU-437.64—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeTrans-MT-LargeSmoothed BLEU-423.57—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeTrans-MT-BaseSmoothed BLEU-413.37—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeTrans-MT-TF-LargeSmoothed BLEU-419.98—Unverified