The Construction Of Cyrillic Mongolian Homographs Knowledge Base

With the development of language information processing,the construction of the knowledge based resources are also needed to be developed at the same time.The construction of traditional Mongolian knowledge based resources has taken an important role in the field of syntax and semantics.But the Cyrillic Mongolian Knowledge base is not enough yet.In this paper,we get the homograph from the "Mongolian Dictionary","The New Mongolian Chinese Dictionary","The Mongolian Chinese Dictionary","Generalized Mongolian Dictionary" to establish the "Cyrillic Mongolian collocation words library".What's more,according to this dictionary,we built the "Cyril Mongolian collocation words library" which is based on the dictionary and "Cyril Mongolian collocation word library" which is based on the corpus.There are five parts in this paper,the introduction,chapter one,chapter two,chapter three and the conclusion.In the introduction,we introduced the purpose of this research,the general situation of the research and the method we use in this research.In chapter one,we discuss the Cyrillic Mongolian Homographs' definition,classification and relationship with polysemy and multi-category words from the aspect of language information processing.In chapter two,we revealed the process of the establishment of "Cyril Mongolian word information dictionary",which included the source term,selecting principle,the problems we encountered and the solutions.At last,we introduced the property fields and value specification of the "Cyrillic Mongolian homograph information dictionary".In chapter three,we showed the process and method of how to build the "Cyril Mongolian collocation word library" that is based both on the dictionary and corpus.In the conclusion,we summarized the research work of this paper.At the same time,we put forward the relevant problems and some research work we need to do in the future.