Automatic segmentation of Chinese chunks using a neural network

Abstract

介绍一种基于三层神经元网络的汉语组块自动划分方法。输入信息为句子中每一个字本身及与前后字组合的划分情况,输出为句子中每个字的划分结果。对于一个新输入的汉语句子,在该方法中,并不对句子进行切词,这是与别的组块分析方法的不同之处。实验表明,该方法是可行的,也是有效的。 This paper presents a method for automatic segmentation of Chinese chunks based on 3-layer neural networks. The corpus has been processed with Chinese word segmentation and phrase identification and tagging. In the neural networks model, the input data is the segmentation situation of every character and its combinations with neighbor characters in a Chinese sentence. The output is the segmentation results of every character in a Chinese sentence. The preliminary results show that the method is feasible and effective.