EditSum: A Retrieve-and-Edit Framework for Source Code Summarization

Li, Jia; Li, Yongmin; Li, Ge; Hu, Xing; Xia, Xin; Jin, Zhi

doi:10.1109/ase51524.2021.9678724

Cited by 39 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous work [11]- [13], the traditional termbased retrieval techniques (e.g., TF-IDF [14] and BM25 [15]) have been widely used. Although the term-based retrieval methods have the advantages of time-saving and convenience, it has been pointed out that they may cause the model to fail to converge [12] or hurt the model performance [16] since they cannot exploit semantic-level features of the code and comments, and are prone to retrieval of dissimilar data. To alleviate this problem, we employ the Dense Passage Retriever (DPR) [3] model as the retriever.…”

Section: A Exemplar Retrievermentioning

confidence: 99%

Developer-Intent Driven Code Comment Generation

Mu¹,

Chen²,

Shi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Existing automatic code comment generators mainly focus on producing a general description of functionality for a given code snippet without considering developer intentions. However, in real-world practice, comments are complicated, which often contain information reflecting various intentions of developers, e.g., functionality summarization, design rationale, implementation details, code properties, etc. To bridge the gap between automatic code comment generation and realworld comment practice, we define Developer-Intent Driven Code Comment Generation, which can generate intent-aware comments for the same source code with different intents. To tackle this challenging task, we propose DOME, an approach that utilizes Intent-guided Selective Attention to explicitly select intent-relevant information from the source code, and produces various comments reflecting different intents. Our approach is evaluated on two real-world Java datasets, and the experimental results show that our approach outperforms the state-of-the-art baselines. A human evaluation also confirms the significant potential of applying DOME in practical usage, enabling developers to comment code effectively according to their own needs.

show abstract

Section: A Exemplar Retrievermentioning

confidence: 99%

Developer-Intent Driven Code Comment Generation

Mu¹,

Chen²,

Shi³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…code repair [25,46], code summarization [23,28], code search [8,20]. In this paper, we conduct the poison attack and defense on three representative source code processing tasks (i.e., defect detection, clone detection, and code repair).…”

Section: Deep Learning For Source Code Processingmentioning

confidence: 99%

“…With the data support of open-source software repositories, the DL models have achieved state-of-the-art (SOTA) results on various source code processing tasks such as defect detection [32,60], clone detection [51,58], code repair [ 25,46]), and code summarization [23,28]. Some of these techniques have further been developed as industrial solutions to accelerate software development productivity such as the code completion toolkits Copilot [1] and IntelliCode [3].…”

Section: Introductionmentioning

confidence: 99%

Poison Attack and Defense on Deep Source Code Processing Models

Li¹,

Li²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

In the software engineering (SE) community, deep learning (DL) has recently been applied to many source code processing tasks, achieving state-of-the-art results. Due to the poor interpretability of DL models, their security vulnerabilities require scrutiny. Recently, researchers have identified an emergent security threat in the DL field, namely poison attack. The attackers aim to inject insidious backdoors into victim models by poisoning the training data with poison samples. Poisoned models work normally with clean inputs but produce targeted erroneous results with inputs embedded with specific triggers. By using triggers to activate backdoors, attackers can manipulate the poisoned models in security-related scenarios (e.g., defect detection) and lead to severe consequences.To verify the vulnerability of existing deep source code processing models to the poison attack, we firstly present a poison attack framework for source code named CodePoisoner as a strong imaginary enemy. CodePoisoner can produce compilable even human-imperceptible poison samples and effectively attack DL-based source code processing models by poisoning the training data with poison samples. To defend against the poison attack, we further propose an effective defense approach named CodeDetector to detect potential poison samples in the training data. CodeDetector can be applied to many model architectures (e.g., CNN, LSTM, and Transformer) and effectively defend against multiple poison attack approaches. We apply our CodePoisoner and CodeDetector to three tasks, including defect detection, clone detection, and code repair. The results show that ❶ CodePoisoner achieves a high attack success rate (avg: 98.3%, max: 100%) in misleading victim models to targeted erroneous behaviors. It validates that existing deep source code processing models have a strong vulnerability to the poison attack. ❷ CodeDetector effectively defends against multiple poison attack approaches by detecting (max: 100%) poison samples in the training data. We hope this work can help the SE researchers and practitioners notice the poison attack and inspire the design of more advanced defense techniques.

show abstract

“…EDITSUM is a new retrieval and editing method for code summaries, consisting of a retrieval module and an editing module [25]. The model uses Adam as the optimizer, setting the learning rate to 0.001.…”

Section: Baselinesmentioning

confidence: 99%

MMF3: Neural Code Summarization Based on Multi-Modal Fine-Grained Feature Fusion

Gao

Lyu

et al. 2022

Proceedings of the 16th ACM / IEEE International Symposium on Empirical Software Engineering and Measurement

View full text Add to dashboard Cite

Background: Code summarization automatically generates the corresponding natural language descriptions according to the input code to characterize the function implemented by source code. Comprehensiveness of code representation is critical to code summarization task. However, most existing approaches typically use coarse-grained fusion methods to integrate multi-modal features. They generally represent different modalities of a piece of code, such as an Abstract Syntax Tree (AST) and a token sequence, as two embeddings and then fuse the two ones at the AST/code levels. Such a coarse integration makes it difficult to learn the correlations between fine-grained code elements across modalities effectively. Aims: This study intends to improve the model's prediction performance for high-quality code summarization by accurately aligning and fully fusing semantic and syntactic structure information of source code at node/token levels. Method: This paper proposes a Multi-Modal Fine-grained Feature Fusion approach (MMF3) for neural code summarization. The method uses the Transformer architecture. In particular, we introduce a novel fine-grained fusion method, which allows fine-grained fusion of multiple code modalities at the token and node levels. Specifically, we use this method to fuse information from both token and AST modalities and apply the fused features to code summarization. Results: We conduct experiments on one Java and one Python datasets, and evaluate generated summaries using four metrics. The results show that: 1) the performance of our model outperforms the current stateof-the-art models, and 2) the ablation experiments show that our proposed fine-grained fusion method can effectively improve the accuracy of generated summaries. Conclusion: MMF3 can mine the relationships between cross-modal elements and perform accurate fine-grained element-level alignment fusion accordingly.

show abstract

EditSum: A Retrieve-and-Edit Framework for Source Code Summarization

Cited by 39 publications

References 31 publications

Developer-Intent Driven Code Comment Generation

Developer-Intent Driven Code Comment Generation

Poison Attack and Defense on Deep Source Code Processing Models

MMF3: Neural Code Summarization Based on Multi-Modal Fine-Grained Feature Fusion

Contact Info

Product

Resources

About