人脑输入汉语文本识别分词时的假象分析

How the Cerebrum Distinguishes False Appearance in Separating Words from Sentences in Chinese Texts

为了使中文信息处理中关于分词问题的研究从人脑的分词机制中得到参照,我们探索了人脑在给汉语书面语分词时识别词的交叉和包孕假象的过程,包括以下4个问题:1.人脑在输入汉语文本时可能遇到的词的交叉和包孕假象及这些假象形成的原因;2.人脑识别词的假象的范围和途径;3.人脑识别词的假象所需要的知识和能力;4.人脑的言语场。

This paper explores the process of the cerebrum distinguishing the false appearance of intersection and container when it separates words from sentences in Chinese texts in order to render a reference for the study of separating words on NLP from functions of cerebrum separating words. This article deals with these four problems： First,The false appearances of intersection and container that cerebrum meeta when reading a Chinese text and the causes bringing about these appearances; Second, the scope and ways in which cerebrum distinguishes the false appearances; Third, knowledge and capability needed for the cerebrum to distinguish the false appearances of words ;Fourth, the speech field of cerebrum.