A Noise-tolerant Differentiable Learning Approach for Single Occurrence Regular Expression with Interleaving

no code implementations • 1 Dec 2022 • Rongzhen Ye, Tianqu Zhuang, Hai Wan, Jianfeng Du, Weilin Luo, Pingjia Liang

We design a neural network to simulate SOIRE matching and theoretically prove that certain assignments of the set of parameters learnt by the neural network, called faithful encodings, are one-to-one corresponding to SOIREs for a bounded size.