摘要
该文以社会语言学和计算语言学相结合的角度,根据乌兹别克语言特点提出乌兹别克语"词干(词根)+词缀+词尾"的词法结构模型、构词模型及名词构形词缀规律,为了计算机处理方便,将原来的六种格扩充十种格,为下一步开展词干提取、词性标注等乌兹别克语自然语言处理技术的研究提供基础支撑。
This paper takes the perspective of social linguistics and computational linguistics, according to the characteristics of Uz-bek language Uzbek "stem(root) + affix and suffix" lexical structure model, the formation model and configuration of terms affixrules, convenient for computer processing, the original expansion of ten kinds of six frames. It will provide a basis for the further re-search on the processing technology of Uzbek natural language such as word stem extraction and word tagging.
引文
[1]早克热·卡德尔,艾山·吾买尔,吐尔根·依布拉音,帕里旦·吐尔逊,吴小川.混合策略的维吾尔语名词词干提取系统[J].计算机工程与应用.2013,49(1).
[2]塔依尔·阿不都外力,艾山·吾买尔,吐尔根·依布拉音,张健.基于标注词典和规则的维吾尔文动词词干提取方法[J].新疆大学学报,2013,30(1).
[3]古丽巴努木·克拜吐里.乌孜别克语教程[M].北京:中央民族大学出版社,2016.
[4]哈米提·铁木尔.现代维吾尔语语法学[M].北京:民族出版社,2011.
[5]哈米提·铁木尔.关于维吾尔语名词“格”的范畴[J].新疆大学学报,1980(3).
[6]高莉琴,阿不都许库尔·艾山.关于维语的词类划分问题[J].新疆大学学报,1987(3).