Filters








228,622 Hits in 4.6 sec

A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques

Xiaotao Song, Hailong Sun, Xu Wang, Jiafei Yan
2019 IEEE Access  
To solve these problems of code comments, researchers have been concerned with generating code comments automatically.  ...  In this work, we aim at conducting a survey of automatic code commenting researches. First, we generally analyze the challenges and research framework of automatic generation of program comments.  ...  When N-gram model is used to solve automatic comment generation problems, it is usually used to assist other statistical model to analyze source code, or train source code models.  ... 
doi:10.1109/access.2019.2931579 fatcat:gzwjs6wnerec3nlciqmrvpbsz4

CloCom: Mining existing source code for automatic comment generation

Edmund Wong, Taiyue Liu, Lin Tan
2015 2015 IEEE 22nd International Conference on Software Analysis, Evolution, and Reengineering (SANER)  
We manually evaluate the generated code comments and find that only 23.7% of the generated code comments are good.  ...  In our evaluation, we analyze 42 million lines of code from 1,005 open source projects from GitHub, and use them to generate 359 code comments for 21 Java projects.  ...  Although human written sentences from Stack Overflow can be used as source code comments, the technique can only generate a limited number of comments automatically.  ... 
doi:10.1109/saner.2015.7081848 dblp:conf/wcre/WongLT15 fatcat:xcp7rz5y3rda3b747w44sv2bn4

Comment Generation for Source Code: State of the Art, Challenges and Opportunities [article]

Xiaoran Wang, Benwen Zhang
2018 arXiv   pre-print
Among these approaches, comment generation for source code is gaining more and more attention and has become a popular research area.  ...  Developers often use integrated development environments, debuggers, and tools for code search, testing, and program understanding to reduce the tedious tasks.  ...  used question and answer sites for automatic comment generation [52] .  ... 
arXiv:1802.02971v2 fatcat:zj4xhtpecngfbg5qnttiov4a5q

Retrieve and Refine: Exemplar-based Neural Comment Generation [article]

Bolin Wei
2019 arXiv   pre-print
Most previous neural comment generation systems used an encoder-decoder neural network and encoded only information from source code as input. Software reuse is common in software development.  ...  Code comment generation is a crucial task in the field of automatic software development.  ...  Therefore, we argue that it is not enough to generate comments only based on the source code.  ... 
arXiv:1910.10419v1 fatcat:xdue5gms3rbepgu2doufzkko3m

Source code indexing for automated tracing

Anas Mahmoud, Nan Niu
2011 Proceeding of the 6th international workshop on Traceability in emerging forms of software engineering - TEFSE '11  
Requirements-to-source-code traceability employs information retrieval (IR) methods to automatically link requirements to the source code that implements them.  ...  Source code demands special attention in the indexing process. In this paper, we investigate source code indexing for supporting automatic traceability.  ...  Our dependent variable focuses on the quality of the automatically generated candidate requirements-to-source-code traceability links.  ... 
doi:10.1145/1987856.1987859 dblp:conf/icse/MahmoudN11 fatcat:cijkarmucbe27ng4kj6wtszp6m

/*icomment

Lin Tan, Ding Yuan, Gopal Krishna, Yuanyuan Zhou
2007 Proceedings of twenty-first ACM SIGOPS symposium on Operating systems principles - SOSP '07  
This paper takes the first step in automatically analyzing comments written in natural language to extract implicit program rules and use these rules to automatically detect inconsistencies between comments  ...  Commenting source code has long been a common practice in software development. Compared to source code, comments are more direct, descriptive and easy-to-understand.  ...  ACKNOWLEDGMENTS We greatly appreciate our shepherd, Stefan Savage, for his invaluable feedback, precious time, and the anonymous reviewers for their insightful comments.  ... 
doi:10.1145/1294261.1294276 dblp:conf/sosp/TanYKZ07 fatcat:2wen7dwubbh6xarlldpkyp4xhq

A Survey of Automatic Source Code Summarization

Chunyan Zhang, Junchao Wang, Qinglei Zhou, Ting Xu, Ke Tang, Hairen Gui, Fudong Liu
2022 Symmetry  
Given a set of source code, the ASCS techniques can automatically generate a summary described with natural language. In this paper, we give a review of the development of ASCS technology.  ...  Almost all ASCS technology involves the following stages: source code modeling, code summarization generation, and quality evaluation.  ...  We thank the associate editor and the reviewers for their useful feedback that improved this paper.  ... 
doi:10.3390/sym14030471 fatcat:zin2tctfdvgtjjf34o4abwjxvm

Summarizing Source Code with Transferred API Knowledge

Xing Hu, Ge Li, Xin Xia, David Lo, Shuai Lu, Zhi Jin
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Code summarization, aiming to generate succinct natural language description of source code, is extremely useful for code search and code comprehension.  ...  about the functionality of the source code.  ...  Results show that using RNN to encode the source code (Code-Only) or API sequences (API-Only) outperforms using the embeddings of tokens directly (CODE-NN).  ... 
doi:10.24963/ijcai.2018/314 dblp:conf/ijcai/HuLXLLJ18 fatcat:yp6doniv2jd7njektw2skowimi

Recommendations for Datasets for Source Code Summarization [article]

Alexander LeClair, Collin McMillan
2019 arXiv   pre-print
Source Code Summarization is the task of writing short, natural language descriptions of source code.  ...  The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs.  ...  First, as depicted in Figure 1 , words appear to be used more often in code as compared to natural language -there are fewer words used only one or two times, and in general more used 3+ times.  ... 
arXiv:1904.02660v1 fatcat:qaws7mx67bcorbz2z7eeg7wtb4

Recommendations for Datasets for Source Code Summarization

Alexander LeClair, Collin McMillan
2019 Proceedings of the 2019 Conference of the North  
Source Code Summarization is the task of writing short, natural language descriptions of source code.  ...  The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs.  ...  First, as depicted in Figure 1 , words appear to be used more often in code as compared to natural language -there are fewer words used only one or two times, and in general more used 3+ times.  ... 
doi:10.18653/v1/n19-1394 dblp:conf/naacl/LeClairM19 fatcat:zfk23j4derftdodtrf6kxsacja

Automatic Generation of Text Descriptive Comments for Code Blocks [article]

Yuding Liang, Kenny Q. Zhu
2018 arXiv   pre-print
We propose a framework to automatically generate descriptive comments for source code blocks.  ...  Our framework does not rely on any template, but makes use of a new recursive neural network called Code-RNN to extract features from the source code and embed them into one vector.  ...  To automatically generate descriptive comments from source code, one needs a way of accurately representing A comment here refers to the description at the beginning of a method, with more than eight words  ... 
arXiv:1808.06880v1 fatcat:wklcowtffzfazkuxcc75g7n7vy

Automatic Code Summarization: A Systematic Literature Review [article]

Yuxiang Zhu, Minxue Pan
2019 arXiv   pre-print
High-quality comments can help us better understand programs, but they're often missing or outmoded in today's programs. Automatic code summarization is proposed to solve these problems.  ...  Method: In this paper, we performed a systematic literature review over the automatic source code summarization field.  ...  The search terms included code summarization, summarize code, code mining, automatic document source code, comment generation and summarizing source code change.  ... 
arXiv:1909.04352v2 fatcat:xdxfdihcdfhbfnnilc2ofif4le

Deep code comment generation

Xing Hu, Ge Li, Xin Xia, David Lo, Zhi Jin
2018 Proceedings of the 26th Conference on Program Comprehension - ICPC '18  
This paper proposes a new approach named DeepCom to automatically generate code comments for Java methods. The generated comments aim to help developers understand the functionality of Java methods.  ...  We use a deep neural network that analyzes structural information of Java methods for better comments generation.  ...  Automatic generation of code comments can not only save developers' time in writing comments, but also help in source code understanding.  ... 
doi:10.1145/3196321.3196334 dblp:conf/iwpc/HuLXLJ18 fatcat:kcbc6boulrgtpdnf4fhcu242bq

Identifying Auto-Generated Code by Using Machine Learning Techniques

Kento Shimonaka, Soichi Sumi, Yoshiki Higo, Shinji Kusumoto
2016 2016 7th International Workshop on Empirical Software Engineering in Practice (IWESEP)  
Therefore, we propose a technique to identify auto-generated code automatically by using machine learning techniques.  ...  A usual way to remove auto-generated code is searching particular comments which exist among auto-generated code.  ...  Consequently, in this paper, we propose a technique to identify auto-generated code automatically even if they do not have code comments.  ... 
doi:10.1109/iwesep.2016.18 dblp:conf/wcre/ShimonakaSHK16 fatcat:nejyhr66ezbsfahuzx7pskvr2a

Automatic comment generation for source code using external information by neural networks for computational thinking

Hiromitsu Shiina, Sakuei Onishi, Akiyoshi Takahashi, Nobuyuki Kobayashi
2020 International journal of smart computing and artificial intelligence  
As a method, we learn the source code and comment pair by Encoder-Decoder translation model using LSTM, thereby generating comments of the source code that was the target of learning.  ...  To support the understanding of programs and understanding of procedures, we think need to automatically generate comments from source code.  ...  Automatic Comment Generation for Source Code Using External Information by Neural Networks for Computational Thinking Bl Source code Generate comments by Evaluation ock Encoder-Decoder (1-6) 0  ... 
doi:10.52731/ijscai.v4.i2.572 fatcat:rebnt6w3hna6vpq3risnqk3epq
« Previous Showing results 1 — 15 out of 228,622 results