English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Software defects consume 40% of the total budget in software development andcost the global economy billions of dollars every year. Unfortunately, despitethe use of many software quality assurance (SQA) practices in softwaredevelopment (e.g., code review, continuous integration), defects may stillexist in the official release of a software product. Therefore, prioritizingSQA efforts for the vulnerable areas of the codebase is essential to ensure thehigh quality of a software release. Predicting software defects at the linelevel could help prioritize the SQA effort but is a highly challenging taskgiven that only ~3% of lines of a codebase could be defective. Existing workson line-level defect prediction often fall short and cannot fully leverage theline-level defect information. In this paper, we propose Bugsplorer, a noveldeep-learning technique for line-level defect prediction. It leverages ahierarchical structure of transformer models to represent two types of codeelements: code tokens and code lines. Unlike the existing techniques that areoptimized for file-level defect prediction, Bugsplorer is optimized for aline-level defect prediction objective. Our evaluation with five performancemetrics shows that Bugsplorer has a promising capability of predictingdefective lines with 26-72% better accuracy than that of the state-of-the-arttechnique. It can rank the first 20% defective lines within the top 1-3%suspicious lines. Thus, Bugsplorer has the potential to significantly reduceSQA costs by ranking defective lines higher.

Predicting Line-Level Defects by Capturing Code Contexts with Hierarchical Transformers