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 clones are often introduced when developers reuse code fragments toimplement similar functionalities in the same or different software systems.Many high-performing clone detection tools today are based on deep learningtechniques and are mostly used for detecting clones written in the sameprogramming language, whereas clone detection tools for detectingcross-language clones are also emerging rapidly. The popularity of deeplearning-based clone detection tools creates an opportunity to investigate howknown strategies that boost the performances of deep learning models could befurther leveraged to improve clone detection tools. In this paper, weinvestigate such a strategy, data augmentation, which has not yet been exploredfor cross-language clone detection as opposed to single-language clonedetection. We show how the existing knowledge on transcompilers(source-to-source translators) can be used for data augmentation to boost theperformance of cross-language clone detection models, as well as to adaptsingle-language clone detection models to create cross-language clone detectionpipelines. To demonstrate the performance boost for cross-language clonedetection through data augmentation, we exploit Transcoder, which is apre-trained source-to-source translator. To show how to extend single-languagemodels for cross-language clone detection, we extend a popular single-languagemodel, Graph Matching Network (GMN) in a combination with the transcompilers.We evaluated our models on popular benchmark datasets. Our experimental resultsshowed improvements in F1 scores (sometimes up to 3%) for the cutting-edgecross-language clone detection models. Even when extending GMN forcross-language clone detection, the models built leveraging data augmentationoutperformed the baseline with scores of 0.90, 0.92, and 0.91 for precision,recall, and F1 score, respectively.

Pathways to Leverage Transcompiler based Data Augmentation for Cross-Language Clone Detection