Write a Blog >>
ICSE 2021
Sun 16 May - Sat 5 June 2021

This program is tentative and subject to change.

Since regular expressions (abbrev. regexes) are difficult to understand and compose, automatically generating regexes has been an important research problem. This paper introduces TransRegex, for automatically constructing regexes from both natural language descriptions and examples. To the best of our knowledge, TransRegex is the first to treat the NLP-and-example-based regex synthesis problem as the problem of NLP-based synthesis with regex repair. For this purpose, we present novel algorithms for both NLP-based synthesis and regex repair. We evaluate TransRegex with ten relevant state-of-the-art tools on three publicly available datasets. The evaluation results demonstrate that the accuracy of our TransRegex is 17.4%, 35.8% and 38.9% higher than that of NLP-based approaches on the three datasets, respectively. Furthermore, TransRegex can achieve higher accuracy than the state-of-the-art multi-modal techniques with 10% to 30% higher accuracy on all three datasets. The evaluation results also indicate TransRegex utilizing natural language and examples in a more effective way.

This program is tentative and subject to change.

Wed 26 May
Times are displayed in time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

12:55 - 13:55
2.2.4. Programming: General IssuesTechnical Track at Blended Sessions Room 4
Chair(s): Gregorio RoblesUniversidad Rey Juan Carlos
12:55
20m
Paper
Efficient Compiler Autotuning via Bayesian OptimizationTechnical Track
Technical Track
Junjie ChenCollege of Intelligence and Computing, Tianjin University, Ningxin XuCollege of Intelligence and Computing, Tianjin University, Peiqi ChenCollege of Intelligence and Computing, Tianjin University, Hongyu ZhangThe University of Newcastle
Pre-print
13:15
20m
Paper
TransRegex: Multi-modal Regular Expression Synthesis by Generate-and-RepairTechnical Track
Technical Track
Yeting LiInstitute of Software, Chinese Academy of Sciences;University of Chinese Academy of Sciences, Shuaimin LiSchool of Computer Science and Technology, University of Chinese academy of sciences, Zhiwu XuShenzhen University, Shenzhen, China, Jialun CaoDepartment of Computer Science and Engineering, The Hong Kong University of Science and Technology, Zixuan ChenInstitute of Software, Chinese Academy of Sciences;University of Chinese Academy of Sciences, Yun HuInstitute of Software, Chinese Academy of Sciences;University of Chinese Academy of Sciences, Haiming ChenInstitute of Software, Chinese Academy of Sciences;University of Chinese Academy of Sciences, Shing-Chi CheungDepartment of Computer Science and Engineering, The Hong Kong University of Science and Technology
Pre-print
13:35
20m
Paper
EvoSpex: An Evolutionary Algorithm for Learning PostconditionsArtifact ReusableTechnical Track
Technical Track
Facundo MolinaUniversity of Rio Cuarto and CONICET, Argentina, Pablo PonzioDept. of Computer Science FCEFQyN, University of Rio Cuarto, Nazareno AguirreUniversity of Rio Cuarto and CONICET, Argentina, Marcelo F. FriasDept. of Software Engineering Instituto Tecnológico de Buenos Aires
Pre-print