상세 보기
Deep learning-based logging recommendation using merged code representation
- Lee, S.;
- Lee, Y.;
- Lee, C.-G.;
- Woo, H.
Citations
WEB OF SCIENCE
0Citations
SCOPUS
1초록
When developing a large scale software product, it is essential to share a common set of structural coding guidelines and standards among the project team members. In this paper, we propose MergeLogging, a deep learning-based merged network using various code representations for automated logging decisions or other tasks. MergeLogging archives the enhanced recommendation ability that utilizes orthogonal code features from code representations. Our case study with three open-source project datasets demonstrates that logging accuracy can reach as high as 93%.
키워드
Code embedding; Deep learning; Logging recommendation; Open source software; Code representation; Open source projects; Orthogonal code; Project team; Software products; Deep learning
- 제목
- Deep learning-based logging recommendation using merged code representation
- 저자
- Lee, S.; Lee, Y.; Lee, C.-G.; Woo, H.
- 발행일
- 2021-12
- 유형
- Conference Paper
- 권
- 712
- 페이지
- 49 ~ 53