Xi Ding
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xi Ding has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Xiangping Chen
Sun Yat-sen University
4 shared publications - Yuan Huang
Sun Yat-sen University
4 shared publications - Zibin Zheng
Sun Yat-Sen University, Guangzhou, China
3 shared publications - Hanyang Guo
Sun Yat-sen University, Zhuhai, China
2 shared publications - Jing Bian
Sun Yat-sen University
2 shared publications - Xiaocong Zhou
Sun Yat-sen University
2 shared publications
Latest Publications
- Open Access
- 27 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 33 (6) , 1-35
Do Code Summarization Models Process Too Much Information? Function Signature May Be All That Is Needed
With the fast development of large software projects, automatic code summarization techniques, which summarize the main functionalities of a piece of code using natural languages as comments, play essential roles in helping developers understand and maintain large software projects. Many research efforts have been devoted to building automatic code summarization approaches. Typical code summarization approaches are based on deep learning models. They transform the task into a sequence-to-sequence task, which inputs source code and outputs summarizations in natural languages. All code summarization models impose different input size limits, such as 50 to 10,000, for the input source code. However, how the input size limit affects the performance of code summarization models still remains under-explored. In this article, we first conduct an empirical study to investigate the impacts of different input size limits on the quality of generated code comments. To our surprise, experiments on multiple models and datasets reveal that setting a low input size limit, such as 20, does not necessarily reduce the quality of generated comments. Based on this finding, we further propose to use function signatures instead of full source code to summarize the main functionalities first and then input the function signatures into code summarization models. Experiments and statistical results show that inputs with signatures are, on average, more than 2 percentage points better than inputs without signatures and thus demonstrate the effectiveness of involving function signatures in code summarization. We also invite programmers to do a questionnaire to evaluate the quality of code summaries generated by two inputs with different truncation levels. The results show that function signatures generate, on average, 9.2% more high-quality comments than full code.
- 27 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 33 (6) , 1-35
Open AccessDo Code Summarization Models Process Too Much Information? Function Signature May Be All That Is Needed
With the fast development of large software projects, automatic code summarization techniques, which summarize the main functionalities of a piece of code using natural languages as comments, play essential roles in helping developers understand and maintain large software projects. Many research efforts have been devoted to building automatic code summarization approaches. Typical code summarization approaches are based on deep learning models. They transform the task into a sequence-to-sequence task, which inputs source code and outputs summarizations in natural languages. All code summarization models impose different input size limits, such as 50 to 10,000, for the input source code. However, how the input size limit affects the performance of code summarization models still remains under-explored. In this article, we first conduct an empirical study to investigate the impacts of different input size limits on the quality of generated code comments. To our surprise, experiments on multiple models and datasets reveal that setting a low input size limit, such as 20, does not necessarily reduce the quality of generated comments. Based on this finding, we further propose to use function signatures instead of full source code to summarize the main functionalities first and then input the function signatures into code summarization models. Experiments and statistical results show that inputs with signatures are, on average, more than 2 percentage points better than inputs without signatures and thus demonstrate the effectiveness of involving function signatures in code summarization. We also invite programmers to do a questionnaire to evaluate the quality of code summaries generated by two inputs with different truncation levels. The results show that function signatures generate, on average, 9.2% more high-quality comments than full code.
- Open Access
- 18 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 17-27
Adversarial Attack and Robustness Improvement on Code Summarization
Automatic code summarization, also known as code comment generation, has been proven beneficial for developers to understand better and maintain software projects. However, few research works have investigated the robustness of such models. Robustness requires that the model sustains the quality of the output summaries in the presence of perturbations to the inputs. In this paper, we provide an in-depth study of the robustness of code summarization models. We propose CREATE (Code summaRization modEl’s Adversarial aTtackEr), an approach for performing adversarial attacks against the model. This approach can generate adversarial samples to mislead the model and explore its robustness while ensuring these samples are compilable and semantically similar. We attack mainstream code summarization models with a large-scale available Java dataset to evaluate the effectiveness and efficiency of our approach. The experimental results indicate that CREATE’s attack effectiveness and efficiency surpasses other baselines, causing a decrease in the quality of generated comments by at least 40%. Furthermore, we investigate the magnitude of perturbation caused by CREATE during adversarial attacks, and the results show that the similarity between the adversarial samples generated by CREATE and the input code is approximately 0.8, demonstrating that it induces more minor perturbations compared to other baselines. Finally, we utilize CREATE for adversarial training of the model. Through experimentation, this approach indeed effectively enhances the model’s robustness.
- 18 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 17-27
Open AccessAdversarial Attack and Robustness Improvement on Code Summarization
Automatic code summarization, also known as code comment generation, has been proven beneficial for developers to understand better and maintain software projects. However, few research works have investigated the robustness of such models. Robustness requires that the model sustains the quality of the output summaries in the presence of perturbations to the inputs. In this paper, we provide an in-depth study of the robustness of code summarization models. We propose CREATE (Code summaRization modEl’s Adversarial aTtackEr), an approach for performing adversarial attacks against the model. This approach can generate adversarial samples to mislead the model and explore its robustness while ensuring these samples are compilable and semantically similar. We attack mainstream code summarization models with a large-scale available Java dataset to evaluate the effectiveness and efficiency of our approach. The experimental results indicate that CREATE’s attack effectiveness and efficiency surpasses other baselines, causing a decrease in the quality of generated comments by at least 40%. Furthermore, we investigate the magnitude of perturbation caused by CREATE during adversarial attacks, and the results show that the similarity between the adversarial samples generated by CREATE and the input code is approximately 0.8, demonstrating that it induces more minor perturbations compared to other baselines. Finally, we utilize CREATE for adversarial training of the model. Through experimentation, this approach indeed effectively enhances the model’s robustness.
- Open Access
- 23 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 33 (1) , 1-30
Snippet Comment Generation Based on Code Context Expansion
Code commenting plays an important role in program comprehension. Automatic comment generation helps improve software maintenance efficiency. The code comments to annotate a method mainly include header comments and snippet comments. The header comment aims to describe the functionality of the entire method, thereby providing a general comment at the beginning of the method. The snippet comment appears at multiple code segments in the body of a method, where a code segment is called a code snippet. Both of them help developers quickly understand code semantics, thereby improving code readability and code maintainability. However, existing automatic comment generation models mainly focus more on header comments, because there are public datasets to validate the performance. By contrast, it is challenging to collect datasets for snippet comments, because it is difficult to determine their scope. Even worse, code snippets are often too short to capture complete syntax and semantic information. To address this challenge, we propose a novel S nippet C omment Gen eration approach called SCGen . First, we utilize the context of the code snippet to expand the syntax and semantic information. Specifically, 600,243 snippet code-comment pairs are collected from 959 Java projects. Then, we capture variables from code snippets and extract variable-related statements from the context. After that, we devise an algorithm to parse and traverse abstract syntax tree (AST) information of code snippets and corresponding context. Finally, SCGen generates snippet comments after inputting the source code snippet and corresponding AST information into a sequence-to-sequence-based model. We conducted extensive experiments on the dataset we collected to evaluate our SCGen . Our approach obtains 18.23 in BLEU-4 metrics, 18.83 in METEOR, and 23.65 in ROUGE-L, which outperforms state-of-the-art comment generation models.
- 23 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 33 (1) , 1-30
Open AccessSnippet Comment Generation Based on Code Context Expansion
Code commenting plays an important role in program comprehension. Automatic comment generation helps improve software maintenance efficiency. The code comments to annotate a method mainly include header comments and snippet comments. The header comment aims to describe the functionality of the entire method, thereby providing a general comment at the beginning of the method. The snippet comment appears at multiple code segments in the body of a method, where a code segment is called a code snippet. Both of them help developers quickly understand code semantics, thereby improving code readability and code maintainability. However, existing automatic comment generation models mainly focus more on header comments, because there are public datasets to validate the performance. By contrast, it is challenging to collect datasets for snippet comments, because it is difficult to determine their scope. Even worse, code snippets are often too short to capture complete syntax and semantic information. To address this challenge, we propose a novel S nippet C omment Gen eration approach called SCGen . First, we utilize the context of the code snippet to expand the syntax and semantic information. Specifically, 600,243 snippet code-comment pairs are collected from 959 Java projects. Then, we capture variables from code snippets and extract variable-related statements from the context. After that, we devise an algorithm to parse and traverse abstract syntax tree (AST) information of code snippets and corresponding context. Finally, SCGen generates snippet comments after inputting the source code snippet and corresponding AST information into a sequence-to-sequence-based model. We conducted extensive experiments on the dataset we collected to evaluate our SCGen . Our approach obtains 18.23 in BLEU-4 metrics, 18.83 in METEOR, and 23.65 in ROUGE-L, which outperforms state-of-the-art comment generation models.
- Open Access
- 22 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 32 (5) , 1-26
A Comparative Study on Method Comment and Inline Comment
Code comments are one of the important documents to help developers review and comprehend source code. In recent studies, researchers have proposed many deep learning models to generate the method header comments (i.e., method comment), which have achieved encouraging results. The comments in the method, which is called inline comment, are also important for program comprehension. Unfortunately, they have not received enough attention in automatic generation when comparing with the method comments. In this paper, we compare and analyze the similarities and differences between the method comments and the inline comments. By applying the existing models of generating method comments to the inline comment generation, we find that these existing models perform worse on the task of inline comment generation. We then further explore the possible reasons and obtain a number of new observations. For example, we find that there are a lot of templates (i.e., comments with the same or similar structures) in the method comment dataset, which makes the models perform better. Some terms were thought to be important (e.g., API calls) in the comment generation by previous study does not significantly affect the quality of the generated comments, which seems counter-intuitive. Our findings may give some implications for building the approaches of method comment or inline comment generation in the future.
- 22 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 32 (5) , 1-26
Open AccessA Comparative Study on Method Comment and Inline Comment
Code comments are one of the important documents to help developers review and comprehend source code. In recent studies, researchers have proposed many deep learning models to generate the method header comments (i.e., method comment), which have achieved encouraging results. The comments in the method, which is called inline comment, are also important for program comprehension. Unfortunately, they have not received enough attention in automatic generation when comparing with the method comments. In this paper, we compare and analyze the similarities and differences between the method comments and the inline comments. By applying the existing models of generating method comments to the inline comment generation, we find that these existing models perform worse on the task of inline comment generation. We then further explore the possible reasons and obtain a number of new observations. For example, we find that there are a lot of templates (i.e., comments with the same or similar structures) in the method comment dataset, which makes the models perform better. Some terms were thought to be important (e.g., API calls) in the comment generation by previous study does not significantly affect the quality of the generated comments, which seems counter-intuitive. Our findings may give some implications for building the approaches of method comment or inline comment generation in the future.