Semantic-based extraction approach for generating source code summary towards program comprehension

Kadar, Rozita; Syed-Mohamad, Sharifah Mashita; Rashid, Nur’Aini Abdul

doi:10.1109/mysec.2015.7475208

Cited by 4 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic code summarization is essentially the implementation of a mapping relationship between code and natural language [42]. Maskeri et al [17] proposed using information retrieval techniques for code analysis and proposed a semantic clustering-based strategy to reveal code intent.…”

Section: B Automatic Code Summarizationmentioning

confidence: 99%

A Multi-Module Based Method for Generating Natural Language Descriptions of Code Fragments

Gao

Jiang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Code fragment natural language description generation, also known as code summarization, refers to obtaining a natural language sequence describing a given code fragment's functionality. It is broadly agreed that applying code summarization into production can significantly improve the efficiency of software development and maintenance. In recent years, syntactic analysis (SA) technology and Latent Dirichlet Allocation (LDA) has been widely used in code summarization and has achieved good results. However, most of the existing techniques focus on core code statements, and thus their generated code summarization lacks a logical description of the code fragment's holistic information. To this end, we propose a code summarization method based on multiple modules to generate natural language for each code statement by constructing a new type of natural language template. Meanwhile, to utilize the code fragment's holistic information, we adopt the code statement partition rules and cosine similarity measure to rank and optimize the weight of the overall information of the code fragment, and finally generate the holistic natural language description of the code fragment. The experimental results demonstrate that our method can generate more concise and logical natural language descriptions than existing models.

show abstract

Section: B Automatic Code Summarizationmentioning

confidence: 99%

A Multi-Module Based Method for Generating Natural Language Descriptions of Code Fragments

Gao

Jiang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Extracting knowledge from program requires practically structured code [7]. Program rationality is hard to measure without objective software metrics.…”

Section: Restructuringmentioning

confidence: 99%

Program Comprehension and Analysis

Praveen¹

2016

IJEACS

View full text Add to dashboard Cite

-Due to continuous change in business requirements and to implement proactive, adaptive maintenance procedures in application program; it is required to evolve application program time to time. Program comprehension is a process of program understanding and reverse engineering, which supports the analyst to easily undertake the program for further reengineering. This paper highlights the program elements, components, its analytical solutions for understanding, comprehensions and extension.

show abstract

“…A step-by-step log of commands executed by a program is called a program trace (or just a trace or tracing). The importance of the traces has been frequently mentioned earlier to both developing program code (Abualese et al, 2017;Fittkau et al, 2015;Feng et al, 2018;Kashima et al, 2015;Kadar et al, 2016;Khoury et al, 2017;Khoury et al, 2019;Perez & Abreu, 2016) and programming education (Aggarwal et al, 2018;Paaßen et al, 2016;Srinivasan et al, 2016;Terada, 2005).…”

Section: Introductionmentioning

confidence: 99%

“…Reading source code is an important part of a programmer's work which takes up to half of their working time (Kashima et al, 2015). Plenty of various tools assisting code understanding is developed, see (Kadar et al, 2016;Perez & Abreu, 2016), but they address the needs of experienced developers while learning to read and understand program code is one of the important stages of computer science education. Learning to understand code is difficult for introductory-courses students because it requires simultaneous learning of programming concepts, ways representing algorithms, and programminglanguage syntax.…”

Section: Introductionmentioning

confidence: 99%