Since regular expressions (abbrev. regexes) are dif ficult to understand and compose, automatically generating regexes has been an important research problem. This paper introduces T r a nsRe g e x , lor automatically constructing regexes from both natural language descriptions and examples. To the best of our knowledge, T r a nsRe g e x is the first to treat the Nl.P-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 T r a nsRe g e x with ten relevant state-of-theart tools on three publicly available datasets. The evaluation results demonstrate that the accuracy of our T r a nsRe g e xis 17.4%, 35.8% and 38.9% higher than that of NLP-hased approaches on the three datasets, respectively. Furthermore, T r a nsRe g e x can achieve higher accuracy than the stateof-the-art multi-modal techniques with 10% to 30% higher accuracy on all three datasets. The evaluation results also indicate
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-theart 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 stateof-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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.