信息处理用彝文分词规范研究

Research of the information processing in the Yi language participle normative

自动分词是彝文信息处理领域的一项基础性课题.词类的划分标准是正确切分词乃至以后的词性标注、文字识别、文本校对、机器翻译、篇章理解、自动文摘、文本校对、自动标引等彝文信息处理研究的必要条件.本文首先首先阐述了研究彝文分词规范的必要性和重要意义;然后提出了彝文分词规范的基本原则;讨论了研制彝文分词规范中存在的一些问题。

Automatic word segmentation is a basic subject in Yi language information processing field. The division standard of word segmentation is the necessary condition for Yi language information processing, such as part-of-speech tagging, character recognition, text proofreading, machine translation, discourse understanding, automatic text proofreading, abstract, automatic marking. This paper firstly expounds the necessity and significance of studying norms for Yi language, then puts forward the basic principles for Yi language norms and discusses some related problems.