摘要
文中通过分析藏文文法,提出了自动分解现代藏文字构件的方法,其基本思想是:利用藏文文法将藏文字分解为基本构件和组合构件,并通过建立组合构件属性库进一步将组合构件分解为基本构件,同时确定出各基本构件的位置特征。
Tibetan is one kind of special alphabetic writing that takes the consonant letters as primary components.Tibetan grammar has the characteristic that the word and words-formation should take basic components and its attributes into consideration.Therefore,component decomposition of Tibetan characters is a foundation work to study Tibetan information processing.By analyzing Tibetan grammar,a method of component auto-decomposition of modern Tibetan characters was proposed.The basic way is to decompose Tibetan character into basic components and combination components based on grammar,then establish combination component attribute storehouse and decompose combination components into basic components.The last step is to determine the position characteristic of every basic component.
出处
《青海大学学报（自然科学版）》
2010年第4期83-86,共4页
Journal of Qinghai University(Natural Science)
基金
国家社科基金项目(09XYY024)
青海师范大学科研基金资助项目
关键词
藏文信息处理
构件
前加字
后加字
又后加字
Tibetan information processing
component
former letter
later letter backmost letter
