The Research On Term Synonymous Knowledge Database Construction For Tibetan NLP

Tibetan natural language processing is inseparable from the supporting of Tibetan, and it is always inseparable to let the computer understand the Tibetan without the supporting of different knowledge bases, rule bases and Tibetan semantic repository bases. Therefore, we start our concept from establishing Tibetan repository base to different applicable language units, draw on the results of the current authority of the Chinese information processing theory and research, start from words which are the most basic levels of language units and a few basic phrases to describe the modern Tibetan word character information, the number of syllables, speech classification and labeling, word formation structure, collocation information, semantic representation and other information to establish a Tibetan conceptual synonymous knowledge base." We found from the research that if to make the computer to understand natural language, we have to solve the problem on three planes from the semantic perspective; the first is the meaning of lexical. Lexical meaning is the whole basis to research on semantic system. For this reason, to establish a modern Tibetan semantic dictionary is not only a foundational knowledge engineering, but also a very important basic research in Tibetan national language processing.This paper mainly introduces the introduction in the first chapter, discusses the current research the development of Tibetan language processing. Discuss the lexical words, nouns and synonymous noun with the concept definition, classification and other issues in the third chapter. The fourth chapter of this paper primarily focuses on those issues related to the establishment of Knowledge research fields, respectively, classification and definition and categories of nouns, lexical origin of the Tibetan conceptual synonymous, Statistical methods of word formation, word length and character counts、word frequency and statistical research, semantic knowledge of the Tibetan conceptual synonymous, Senses arrangement of weights and the test corpus for conceptual synonymous vocabulary. The major foothold is on its application of the knowledge base, so we focus on the research on conceptual synonymous base for Tibetan search engines and lexicographer synonyms in the seventh chapter. Finally, as the last chapter, we enumerated the research difficulties and the prospects for the future work.