The Semantic Library Of Tibetan Algal Ornaments Based On WordNet

There are so many words in Tibetan language with a large scope that the y can be said to be all-encompassing even a special subject has been formed t o study algalornament in Tibetan culture,which is called etymology.Together with star arithmetic,poetics,drama,phonology and so on,it constitutes the "s mall Wuming" in Tibetan traditional culture.In practical use,Tibetan algae-dec orated words are more special.After the 13 th century,due to the influence of Indian culture,the use of algal ornaments became popular in Tibetan areas.M any scholars took the use of algal ornaments as fashion and used algal orname nts in a large number of literary styles and articles.So it is a unique phenom enon of Tibetan culture.But up to now,Tibetan scholars have not paid enough attention to Tibetan algal ornament words,and few related studies have been done on it.And also there are only one or two researches on algal decoration words based on computer information processing.Zao decorations are distribut ed in various styles and articles of Tibetan literature.If they cannot understand them,it is difficult to understand them on a certain level.The study of algal ornament on computer processing is a necessary step in Tibetan information p rocessing.Based on the balance of the corpus,this paper deals with the fields of po etry,Buddhism,folk songs,prose,papers,novels and so on.A total of 1782 a lga ornaments were extracted from the 442 corpus,and 1491 of them were ent ered in Microsoft Excel database by hand,translated into English and Chinese,and the meanings of them were annotated.Up to now,the total number of w ords in the thesaurus has been 100000 words.The traditional classification method of Tibetan algal ornaments is mainly based on the species of the same genus or the living environment,and there i s no detailed classification of a semantic category from a particular standpoint.So that the words that belong to the same semantic category can extract diffe rent values on one or some semantic features,so as to highlight the similaritie s and differences between these words.In order to make up for this deficiency,this article is based on the study of the construction of Tibetan algae-word-inf ormation database,and uses the semantic classification system adopted by Zhan Weidong of Peking University for reference.This paper classifies the nouns,v erbs and adjectives of alga words in Tibetan language by semantic classification.In the semantic tagging of numerals and nouns,there are some fuzzy taggin g cases.In this paper,according to its own characteristics and the practical uses of the corpus as the starting point,the algae-decorated words are divided into tw o categories: nouns and numerals(no adjectives and verbs do not do this class ification)and semantic tagging is adjusted and supplemented.According to the characteristics of Tibetan alga ornament words,combined with the semantic re lationship between wordnet and Tibetan vocabulary,this paper selects four kind s of semantics that are suitable for Tibetan algaea words.The set of 700 syno nyms of 9 attribute fields was obtained,and the semantic library of Tibetan al gal ornaments based on Wordnet was established.The purpose of this paper is to analyze the semantic relationship of Tibetan alga ornaments based on Word net.Its innovation lies in:(1)the abandoning of the deficiency of the tradition al classification method of Tibetan alga ornament words,use of the semantic c lassification system adopted by Zhan Weidong of Peking University for referen ce,combining with the characteristics of Tibetan alga ornament words,they are divided into 2 categories and 57 middle classes with a depth of the level of 8.(2)According to the characteristics of Tibetan alga ornament words,combini ng the semantic relationship between wordnet and Tibetan vocabulary,four kin ds of semantics suitable for Tibetan alga ornament words are selected.The set of 700 synonyms corresponding to the 9 property fields set is obtained.Based on the design principles and methods of Wordnet,this paper obtains Tibetan algae-worded words and analyzes them according to the real corpus i n order to satisfy the scientific and systematic analysis results.It made basic theoretical research and preparation further for the Tibetan language information processing for the modern Tibetan semantic information dictionary.