Using stereotypes in the automatic generation of natural language summaries for C++ methods

Abid, Nahla J.; Dragan, Natalia; Collard, Michael L.; Maletic, Jonathan I.

doi:10.1109/icsm.2015.7332514

Cited by 33 publications

(19 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Abid et al [38] used method stereotypes to find out the lines of code that reflect the main action of a method and used the separate templates for each stereotype to automatically create the summaries using static program analysis.…”

Section: Abstractive Summarization: An Overview In the Context Of Thementioning

confidence: 99%

“…Most of the focus of studies in source code summarization is for C++ and Java language. Studies can be extended for generating the summaries for other object-oriented languages as well [38]. More work on assessing the quality and effectiveness of summaries for maintenance tasks like feature location or debugging is required [24].…”

Section: Source Code Summarizationmentioning

confidence: 99%

“…Eye-tracking studies from different roles like testers, security experts, database experts, etc. need to be compared [38].…”

Section: Summarization Using Eye-tracking Interactionsmentioning

confidence: 99%

See 2 more Smart Citations

Summarization of Software Artifacts : A Review

Gupta¹,

S.K²

2017

IJCSIT

View full text Add to dashboard Cite

Summarization of software artifacts is an ongoing field of research among the software engineering community due to the benefits that summarization provides like saving of time and efforts in various software engineering tasks like code search, duplicate bug reports detection, traceability link recovery, etc. Summarization is to produce short and concise summaries. The paper presents the review of the state of the art of summarization techniques in software engineering context. The paper gives a brief overview to the software artifacts which are mostly used for summarization or have benefits from summarization. The paper briefly describes the general process of summarization. The paper reviews the papers published from 2010 to June 2017 and classifies the works into extractive and abstractive summarization. The paper also reviews the evaluation techniques used for summarizing software artifacts. The paper discusses the open problems and challenges in this field of research. The paper also discusses the future scopes in this area for new researchers.

show abstract

Section: Abstractive Summarization: An Overview In the Context Of Thementioning

confidence: 99%

Section: Source Code Summarizationmentioning

confidence: 99%

See 1 more Smart Citation

Summarization of Software Artifacts : A Review

Gupta¹,

S.K²

2017

IJCSIT

View full text Add to dashboard Cite

show abstract

“…We found strong evidence that developers tend to write their summaries from source-code lines that they read the most (longest gaze time). Therefore, we conclude that gaze time can substantially predict lines that are important for summarizing a method [6,7,11,12,17]. An overarching goal of this paper is to investigate ways to improve existing summarization approaches via findings from the eye-tracking study presented.…”

Section: Introductionmentioning

confidence: 96%

“…One way to overcome this problem is to automatically generate summaries directly from source code. Several approaches are proposed to generate automatic summaries using Natural Language Processing (NLP) [6,7], text retrieval [8,9], and static analysis [10,11]. In order to further improve source code summarization techniques [6][7][8][11][12][13][14][15][16], Rodeghero et al conducted an eye-tracking study [17] to determine the statements and terms (i.e., identifier names) that programmers view as important when they summarize a method.…”

Section: Introductionmentioning

confidence: 99%

Developer Reading Behavior While Summarizing Java Methods: Size and Context Matters

Abid

Sharif

Dragan

et al. 2019

2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)

Self Cite

View full text Add to dashboard Cite

An eye-tracking study of 18 developers reading and summarizing Java methods is presented. The developers provide a written summary for methods assigned to them. In total, 63 methods are used from five different systems. Previous studies on this topic use only short methods presented in isolation usually as images. In contrast, this work presents the study in the Eclipse IDE allowing access to all the source code in the system. The developer can navigate via scrolling and switching files while writing the summary. New eye-tracking infrastructure allows for this improvement in the study environment. Data collected includes eye gazes on source code, written summaries, and time to complete each summary. Unlike prior work that concluded developers focus on the signature the most, these results indicate that they tend to focus on the method body more than the signature. Moreover, both experts and novices tend to revisit control flow terms rather than reading them for a long period. They also spend a significant amount of gaze time and have higher gaze visits when they read call terms. Experts tend to revisit the body of the method significantly more frequently than its signature as the size of the method increases. Moreover, experts tend to write their summaries from source code lines that they read the most.

show abstract

Learning to Generate Comments for API-Based Code Snippets

Lü

Zhao

et al. 2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Using stereotypes in the automatic generation of natural language summaries for C++ methods

Cited by 33 publications

References 21 publications

Summarization of Software Artifacts : A Review

Summarization of Software Artifacts : A Review

Developer Reading Behavior While Summarizing Java Methods: Size and Context Matters

Learning to Generate Comments for API-Based Code Snippets

Contact Info

Product

Resources

About