Code Data Augmentation to Improve Language Model’, s Performance in Requirement to Code Traceability Link Recovery

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Majidzadeh Ali; Ashtiani Mehrdad; Zakeri Nasrabadi Morteza

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Seminar Paper

Paper Information

Seminar: INTERNATIONAL CONFERENCE ON WEB RESEARCH
Year:2023 | Issue:9

Download Full-Text

View:

Download:

Information Seminar Paper

Title

Code Data Augmentation to Improve Language Model’, s Performance in Requirement to Code Traceability Link Recovery

Author(s)

Majidzadeh Ali | Ashtiani Mehrdad | Zakeri Nasrabadi Morteza

Keywords

Software Traceability

Requirements Traceability

Data Augmentation

Language Model

Abstract

Data Augmentation is a method to efficiently use the existing data to train deep neural networks. Maintaining requirement traceability links helps to improve software quality and prevent defects by aiding software development management. To ease this maintenance, automatic link recovery techniques can be used. One of the recent techniques to do this is to use a Language Model. We propose three code Data Augmentation techniques to improve Language Models’,performance in requirement to code traceability link recovery. These three techniques are rename variable, swap operands, and swap statements. These are general techniques that can be implemented for different programming languages, and have the capacity to generate a variety of outputs randomly, which can improve the generalization of the model. The results of the evaluations show that code Data Augmentation improves the Language Model's performance in recovering doc-method links that are similar to requirement-method links. Using code Data Augmentation, the precision is increased from 0. 669 to 0. 722, the recall is increased from 0. 574 to 0. 601, and the Wilcoxon test shows that the improvements are significant.

Cites

No record.

References

No record.

Cite

APA: Copy

Majidzadeh, Ali, Ashtiani, Mehrdad, & Zakeri Nasrabadi, Morteza. (). . . SID. https://sid.ir/paper/1047270/en

Vancouver: Copy

Majidzadeh Ali, Ashtiani Mehrdad, Zakeri Nasrabadi Morteza. . . Available from: https://sid.ir/paper/1047270/en

IEEE: Copy

Ali Majidzadeh, Mehrdad Ashtiani, and Morteza Zakeri Nasrabadi, “,” presented at the . , [Online]. Available: https://sid.ir/paper/1047270/en

Related Journal Papers