Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces ReSyn, a novel divide-and-conquer framework designed to enhance the synthesis of complex regular expressions by breaking down intricate problems into simpler sub-problems. The authors also present Set2Regex, a synthesizer that leverages permutation invariance to improve efficiency and accuracy. Experimental results reveal that ReSyn markedly increases performance across various synthesizers, achieving a new state-of-the-art on challenging benchmarks.
ReSyn transforms regex synthesis by efficiently tackling complex patterns, leading to unprecedented accuracy on real-world benchmarks.
Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity of real-world regexes, such as deeper nesting and frequent use of union operations. To overcome the resulting performance drop, we propose ReSyn, a synthesizer-agnostic divide-and-conquer framework that decomposes complex synthesis problem into manageable sub-problems. We also introduce Set2Regex, a parameter-efficient synthesizer capturing the permutation invariance of examples. Experimental results demonstrate that ReSyn significantly boosts accuracy across various synthesizers, and its combination with Set2Regex establishes a new state-of-the-art on challenging real-world benchmark. The complete source code, datasets, and pre-trained model checkpoints are publicly available at https://github.com/mrseongminkim/ReSyn.