TransRegex: Multi-modal Regular Expression Synthesis by Generate-and-Repair

TL;DR

TransRegex is a novel approach that combines natural language and example inputs to automatically generate and repair regular expressions, significantly improving accuracy over existing methods.

Contribution

It introduces a new NLP-and-example-based regex synthesis framework with algorithms for both generation and repair, outperforming state-of-the-art tools.

Findings

TransRegex achieves 17.4% to 38.9% higher accuracy than NLP-based methods.

It outperforms existing multi-modal techniques by 10% to 30%.

Utilizing natural language and examples more effectively improves regex synthesis.

Abstract

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.