Blogs (1) >>
ICSE 2019
Sat 25 - Fri 31 May 2019 Montreal, QC, Canada
Wed 29 May 2019 16:50 - 17:00 at Viger - SE Datasets, Research Infrastructure, and Methodology Chair(s): Rashina Hoda

Many software engineering data sets, particularly those that demand manual labelling for classification, are necessarily small. As a consequence, several recent software engineering papers have cast doubt on the effectiveness of deep neural networks for classification tasks, when applied to these data sets. We provide initial evidence that recent advances in Natural Language Processing, that allows neural networks to leverage large amount of unlabelled data in a pre-training phase, can significantly improve performance.

Conference Day
Wed 29 May

Displayed time zone: Eastern Time (US & Canada) change

16:00 - 18:00
SE Datasets, Research Infrastructure, and MethodologyJournal-First Papers / New Ideas and Emerging Results / Demonstrations / Papers / Technical Track at Viger
Chair(s): Rashina HodaThe University of Auckland
16:00
20m
Talk
BugSwarm: Mining and Continuously Growing a Dataset of Reproducible Failures and FixesTechnical Track
Technical Track
Naji DmeiriUniversity of California, Davis, David A TomassiUniversity of California, Davis, Yichen WangUniversity of California, Davis, Antara BhowmickUniversity of California, Davis, Yen-Chuan LiuUniversity of California, Davis, Prem DevanbuUniversity of California, Bogdan VasilescuCarnegie Mellon University, Cindy Rubio-GonzálezUniversity of California, Davis
Pre-print
16:20
20m
Talk
DefeXts: A Curated Dataset of Reproducible Real-World Bugs for Modern JVM LanguagesDemos
Demonstrations
Samuel BentonThe University of Texas at Dallas, Ali GhanbariThe University of Texas at Dallas, Lingming Zhang
16:40
10m
Talk
Open Collaborative Data – using OSS principles to share data in SW engineeringNIER
New Ideas and Emerging Results
Per RunesonLund University
16:50
10m
Talk
Leveraging Small Software Engineering Data Sets with Pre-trained Neural NetworksNIER
New Ideas and Emerging Results
Andrea A. Janes, Romain RobbesFree University of Bozen-Bolzano
17:00
20m
Talk
ActionNet: Vision-based Workflow Action Recognition From Programming ScreencastsTechnical Track
Technical Track
Dehai Zhao, Zhenchang XingAustralia National University, Chunyang ChenMonash University, Xin XiaMonash University, Guoqiang LiShanghai Jiao Tong University
17:20
10m
Talk
The ABC of Software Engineering ResearchJournal-First
Journal-First Papers
Klaas-Jan StolUniversity College Cork and Lero, Ireland, Brian FitzgeraldLero - The Irish Software Research Centre and University of Limerick
Link to publication DOI
17:30
10m
Talk
Mining Plausible Hypotheses from the Literature via Meta-AnalysisNIER
New Ideas and Emerging Results
Vladimir Ivanov, Giancarlo SucciInnopolis University, Jooyong YiUNIST (Ulsan National Institute of Science and Technology)
17:40
10m
Talk
Analyzing Families of Experiments in SE: a Systematic Mapping StudyJournal-First
Journal-First Papers
Adrian Santos Parrilla, Omar GomezEscuela Superior Politecnica de Chimborazo Riobamba, Natalia JuristoUniversidad Politecnica de Madrid
17:50
10m
Talk
Discussion Period
Papers