242,948 Hits in 4.1 sec

Improving topic model source code summarization

Paul W. McBurney, Cheng Liu, Collin McMillan, Tim Weninger
2014 Proceedings of the 22nd International Conference on Program Comprehension - ICPC 2014  
In this paper, we present an emerging source code summarization technique that uses topic modeling to select keywords and topics as summaries for source code.  ...  Our approach organizes the topics in source code into a hierarchy, with more general topics near the top of the hierarchy.  ...  In this paper, we present an emerging source code summarization technique that organizes the topics in source code into a hierarchy.  ... 
doi:10.1145/2597008.2597793 dblp:conf/iwpc/McBurneyLMW14 fatcat:4klx2budcne2nnjibiwqyhojbi

A Topic Guided Pointer-Generator Model for Generating Natural Language Code Summaries [article]

Xin Wang, Xin Peng, Jun Sun, Yifan Zhao, Chi Chen, Jinkai Fan
2021 arXiv   pre-print
Code summarization is the task of generating natural language description of source code, which is important for program understanding and maintenance.  ...  In this work, we present a neural network model named ToPNN for code summarization, which uses the topics in a broader context (e.g., class) to guide the neural networks that combine the generation of  ...  [55] used graph-based neural architecture to improve source code summarization. Ahmad et al. [56] applied Transformer model for source code summarization.  ... 
arXiv:2107.01642v1 fatcat:nuxnjbpsjzazpjigkaoupy6azq

Summarization of Software Artifacts : A Review

Som Gupta, Gupta S.K
2017 International Journal of Computer Science & Information Technology (IJCSIT)  
engineering tasks like code search, duplicate bug reports detection, traceability link recovery, etc.  ...  The paper gives a brief overview to the software artifacts which are mostly used for summarization or have benefits from summarization.  ...  They also used this approach to re-document the source code. • Topic Models: It is a statistical model where each document is represented as a set of topics.  ... 
doi:10.5121/ijcsit.2017.9512 fatcat:4unydg54tbh6ji7hstvixyfrsm


Jaroslav Fowkes, Pankajan Chanthirasegaran, Razvan Ranca, Miltiadis Allamanis, Mirella Lapata, Charles Sutton
2016 Proceedings of the 38th International Conference on Software Engineering Companion - ICSE '16  
We present a novel tool, TASSAL, that automatically creates a summary of each source file in a project by folding its least salient code regions.  ...  While modern code editors do provide code folding to selectively hide blocks of code, it is impractical to use as folding decisions must be made manually or based on simple rules.  ...  We are also grateful to Rebecca Mason for letting us adapt her topic model implementation to source code and would like to thank Brian Doll for useful discussions.  ... 
doi:10.1145/2889160.2889171 dblp:conf/icse/FowkesCRALS16 fatcat:rkdizhkud5h3dbrlj5xwd25hay

A Survey of Automatic Source Code Summarization

Chunyan Zhang, Junchao Wang, Qinglei Zhou, Ting Xu, Ke Tang, Hairen Gui, Fudong Liu
2022 Symmetry  
Almost all ASCS technology involves the following stages: source code modeling, code summarization generation, and quality evaluation.  ...  We can think of the source code and the corresponding summarization as being symmetric. However, the existing source code summarization is mismatched with the source code, missing, or out of date.  ...  We thank the associate editor and the reviewers for their useful feedback that improved this paper.  ... 
doi:10.3390/sym14030471 fatcat:zin2tctfdvgtjjf34o4abwjxvm

Autofolding for Source Code Summarization

Jaroslav Fowkes, Pankajan Chanthirasegaran, Razvan Ranca, Miltiadis Allamanis, Mirella Lapata, Charles Sutton
2017 IEEE Transactions on Software Engineering  
We present a novel solution by formulating the problem as a sequence of AST folding decisions, leveraging a scoped topic model for code tokens.  ...  Developers spend much of their time reading and browsing source code, raising new opportunities for summarization methods.  ...  We are also grateful to Rebecca Mason for allowing us to adapt her TopicSum implementation to source code and would like to thank Brian Doll for useful discussions.  ... 
doi:10.1109/tse.2017.2664836 fatcat:agcufezvcjdbnmtlvhwlbr5wdm

Automatic Code Summarization: A Systematic Literature Review [article]

Yuxiang Zhu, Minxue Pan
2019 arXiv   pre-print
Method: In this paper, we performed a systematic literature review over the automatic source code summarization field.  ...  Aims: We studied publications concerning code summarization in the field of program comprehension to investigate state-of-the-art approaches.  ...  [S7] used Latent Dirichlet allocation (LDA) and n-gram models for predicting class comments. They creatively exploited code and text tokens in the code to improve the performance of topic model.  ... 
arXiv:1909.04352v2 fatcat:xdxfdihcdfhbfnnilc2ofif4le

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

Xiaotao Song, Hailong Sun, Xu Wang, Jiafei Yan
2019 IEEE Access  
As an integral part of source code files, code comments help improve program readability and comprehension.  ...  Finally, we summarize some future directions for advancing the techniques of automatic generation of code comments and the quality assessment of comments.  ...  [80] improve automatic code summarization. They employ one LSTM model to represent the sequential information of code, and another AST-based LSTM model to represent the structure of source code.  ... 
doi:10.1109/access.2019.2931579 fatcat:gzwjs6wnerec3nlciqmrvpbsz4

CodeSum: Translate Program Language to Natural Language [article]

Xing Hu, Yuhan Wei, Ge Li, Zhi Jin
2018 arXiv   pre-print
In this paper, we propose a new code summarization model named CodeSum.  ...  Therefore, as a critical task in software engineering, code summarization aims to generate brief natural language descriptions for source code.  ...  Some traditional approaches such as topic models and keyword extractor have been used in some studies on generating source code summarization. ) uses a topic model to select keywords and topics as summaries  ... 
arXiv:1708.01837v2 fatcat:4d7lgq2ds5g6fpbghf6jsspzqi

Natural language processing in mining unstructured data from software repositories: a review

Som Gupta, S K Gupta
2019 Sadhana (Bangalore)  
The paper mainly focuses on sentiment analysis, summarization, traceability, norms mining and mobile analytics.  ...  With the increasing popularity of open-source platforms, software data is easily available from various open-source tools like GitHub, CVS, SVN, etc.  ...  Automatic source code summarization is to create a brief summary of the source code that describes the methods, functions, calls, etc.  ... 
doi:10.1007/s12046-019-1223-9 fatcat:agssr4ggozendduyxjk3wc6lru

The COST-277 European Action: An Overview [chapter]

Marcos Faundez-Zanuy, Unto Laine, Gernot Kubin, Stephen McLaughlin, Bastiaan Kleijn, Gerard Chollet, Bojan Petek, Amir Hussain
2006 Lecture Notes in Computer Science  
The "coded speech" refers to a plurality of different coding methods and parametric representations.  ...  This paper summarizes the rationale for proposing the COST-277 "nonlinear speech processing" action, and the work done during these last four years.  ...  This has let to deal and study new research topics, summarized in section 4.3.  ... 
doi:10.1007/11613107_1 fatcat:5vthiqrjd5h7nn3jujslsza644

Code to Comment Translation: A Comparative Study on Model Effectiveness Errors [article]

Junayed Mahmud, Fahim Faisal, Raihan Islam Arnob, Antonios Anastasopoulos, Kevin Moran
2021 arXiv   pre-print
Automated source code summarization is a popular software engineering research topic wherein machine translation models are employed to "translate" code snippets into relevant natural language descriptions  ...  Therefore, in this work, we perform both a quantitative and qualitative comparison of three recently proposed source code summarization models.  ...  how future code summarization techniques might be improved.  ... 
arXiv:2106.08415v1 fatcat:zouqwm43djdm7mxbm6h4gpkqgu

A Literature Review of Research in Bug Resolution: Tasks, Challenges and Future Directions

Tao Zhang, He Jiang, Xiapu Luo, Alvin T.S. Chan
2015 Computer journal  
., bug report, source code and change history) in bug repositories to complete the bug resolution task. However, a mountain of submitted bug reports every day increase the developers' workload.  ...  code (i.e., SOURCE).  ...  In this study, they adopted GibbsLDA++ to find the topics from the source code files as well as get the term-topic and topic-document (i.e., bug report) probability distributions.  ... 
doi:10.1093/comjnl/bxv114 fatcat:r4t6kgzqi5cq7nlwuanednwkhq

Guest editorial: special section on software maintenance and evolution

Massimiliano Di Penta, Jonathan I. Maletic
2015 Empirical Software Engineering  
Topics range from reverse engineering, program comprehension, software migration, refactoring, and regression testing.  ...  described in the IEEE Standard Glossary of Software Engineering Terminology (1994), software maintenance is "The process of modifying a software system or component after delivery to correct faults, improve  ...  the authors make use of topic models and investigate how professional and open source developers consider the relevancy of topics extracted from issue reports and how such topics reflect activities mined  ... 
doi:10.1007/s10664-015-9382-8 fatcat:ua3caockmnhjtiil6ceh54t5l4

A Topic Information Fusion and Semantic Relevance for Text Summarization

Fucheng You, Shuai Zhao, Jingjing Chen
2020 IEEE Access  
A high-quality summarization system needs to focus on the topic content of the document and the similarity between the summary and the source document.  ...  The experimental data indicate that the ROUGE index and readability have improved in this model, so these shreds of evidence suggest that the method proposed by our model is sufficient.  ...  CGU [45] : A framework of global coding is introduced to perform global coding to improve the representation effect of source information.  ... 
doi:10.1109/access.2020.2999665 fatcat:6ay5h2jtj5dhna4p7yah42ar3y
« Previous Showing results 1 — 15 out of 242,948 results