MLRegTest：机器学习正则语言的基准测试（英文版）

英文标题：MLRegTest: A Benchmark for the Machine Learning of Regular Languages中文摘要：本文提出了一种名为 MLRegTest 的新的机器学习系统性能基准测试，用于评估序列分类等不同模型在不同的正则语言种类及复杂程度情境下对长距离依赖关系的学习能力，结果表明神经网络的性能取决于测试集的种类、语言类别和神经网络的架构。英文摘要：Evaluating machine learning (ML) systems on their ability to learn knownclassifiers allows fine-grained examination of the patterns they can learn,which builds confidence when they are applied to the learning of unknownclassifiers. This article presents a new benchmark for ML systems on sequenceclassi