摘要
藏文自动排序是藏语自然语言处理领域一项重要的基础研究工作,在词典编纂、信息检索和日常办公等方面具有重要的应用价值。藏文特殊的二维非线性组合方式、词法规则和词典排序规则使得藏文自动排序比其他语种的排序更加复杂。文章对已有研究提出的藏文自动排序方法、规则、算法和模型等进行了较为全面的分析与总结,为研究人员了解藏文自动排序中的构件识别、排序规则和方法以及优化藏文自动排序相关工作提供参考。
Tibetan automatic sorting is an important research work in the field of Tibetan natural language processing,and it has practical applications in lexicography,information retrieval,and daily office work.Tibetan's unique two-dimensional nonlinear combination,as well as its lexical rules and dictionary sorting rules,make Tibetan automatic sorting more complex and difficult compared to other languages.This paper comprehensively analyzed and summarized the methods,rules,algorithms,and models of Tibetan automatic sorting proposed in previous studies,which provides a reference for researchers seeking to understand component identification,sorting rules,and methods in Tibetan automatic sorting and the optimization of Tibetan automatic sorting.
作者
才让叁智
仁青东主
多拉
洛桑嘎登
仁增多杰
Cairang-Sanzhi;Rinchen-Dongrub;Dolha;Luosang-Gadeng;Renzeng-Duojie(School of Information Science and Technology,Tibet University,Lhasa 850000,China;Department of Chinese Language and Lliterature,Northwest Minzu University,Lanzhou 730000,China;National and Local Joint Engineering Research Center for Tibetan Information Technology,Tibet University,Lhasa 850000,China;State Key Laboratory of Tibetan Intelligent Information Processing and Application,Qinghai Normal University,Xining 810008,China)
出处
《高原科学研究》
CSCD
2024年第2期106-117,共12页
Plateau Science Research
基金
国家自然科学基金项目(62266037)
西藏大学校级科研培育基金项目(ZDCZJH19-19)
西藏自治区自然基金项目(XZ202101ZR0108G)
省部共建藏语智能信息处理及应用国家重点实验室开放课题项目(2023-Z-006)。
关键词
藏文自动排序
字符优先级
结构优先级
构件比较顺序
Tibetan automatic sorting
character priority
structure priority
component comparison order
