ICSE 2023 (series) / ICPC 2023 (series) / Replications and Negative Results (RENE) /
Naturalness in Source Code Summarization. How Significant is it?
Mon 15 May 2023 16:12 - 16:21 at Meeting Room 106 - Code Summarization and Visualization Chair(s): Banani Roy, Akhila Sri Manasa Venigalla
Research in source code summarization, that is the description of the functionality of a program with short sentences expressed in natural language, is a topic of great interest in the software engineering community, since it can help in automatically generating software documentation, and in general can ease the effort of the developers in understanding the code they are working on. In this paper, we study the existing neural models designed for this purpose, pointing out their high sensitivity to the natural elements present in the source code (i.e. comments and identifiers) and the related drop in performance when such elements are ablated or masked.
We then propose a novel source code summarization approach based on the aid of an intermediate pseudo-language, through which we are able to fine-tune the BRIO model for natural language on source code summarization, and to achieve results comparable to that obtained by the state-of-the-art source code competitors (e.g. PLBART and CodeBERT). We finally discuss about the limitations of these NLP-based approaches when transferred in the domain of source code processing, and we provide some insights for further research directions.
Mon 15 MayDisplayed time zone: Hobart change
Mon 15 May
Displayed time zone: Hobart change
15:45 - 17:15 | Code Summarization and VisualizationReplications and Negative Results (RENE) / Discussion / Research at Meeting Room 106 Chair(s): Banani Roy University of Saskatchewan, Akhila Sri Manasa Venigalla IIT Tirupati | ||
15:45 9mFull-paper | An Extensive Study of the Structure Features in Transformer-based Code Semantic Summarization Research Kang Yang , Xinjun Mao National University of Defense Technology, Shangwen Wang National University of Defense Technology, Yihao Qin National University of Defense Technology, Yao Lu National University of Defense Technology, Tanghaoran Zhang , Kamal Al-Sabahi University Of Technology and Applied Sciences-ibra Pre-print | ||
15:54 9mFull-paper | Label Smoothing Improves Neural Source Code Summarization Research Sakib Haque University of Notre Dame, Aakash Bansal University of Notre Dame, Collin McMillan University of Notre Dame Pre-print | ||
16:03 9mFull-paper | Interpretation-based Code Summarization Research Mingyang Geng National University of Defense Technology, Shangwen Wang National University of Defense Technology, Dezun Dong NUDT, Haotian Wang National University of Defense Technolog, Shaomeng Cao Peng Cheng Laboratory, Kechi Zhang Peking University, China, Zhi Jin Peking University Pre-print | ||
16:12 9mFull-paper | Naturalness in Source Code Summarization. How Significant is it? Replications and Negative Results (RENE) | ||
16:21 9mFull-paper | Comparing 2D and Augmented Reality Visualizations for Microservice System Understandability: A Controlled Experiment Research Amr Elsayed Baylor University, Tomas Cerny Baylor University, Davide Taibi Tampere University , Sira Vegas Universidad Politecnica de Madrid DOI Pre-print | ||
16:30 9mFull-paper | ChameleonIDE: Untangling Type Errors Through Interactive Visualization and Exploration Research Shuai Fu Monash University, Tim Dwyer Monash University, Peter J. Stuckey Monash University, Jackson Wain Monash University, Jesse Linossier Monash University Pre-print | ||
16:39 36mPanel | Discussion 4 Discussion |