A Study Of Tibetan Interrogative Sentences Based On Syntax Tree Database

Tibetan information processing after more than 20 years of development,the research of "word" and "word" processing has achieved fruitful results,and developed relevant national and international standards.Syntactic analysis is an important topic in the field of Tibetan information processing.Compared with word processing,word processing is more complex,involving lexical analysis,syntactic analysis,semantic understanding and many other aspects.The main goal of syntactic analysis is to enable the computer to understand the meaning of sentences and generate qualified sentences.From the perspective of language information processing,this paper constructs a Tibetan question tagging corpus,formulates a Tibetan question classification system,defines the concept of Tibetan question,and describes the syntactic structure of Tibetan question in detail.First of all,this paper discusses the research background of corpus and the research status at home and abroad,and extracts 5000 Tibetan interrogative sentences from various texts of different subjects for word segmentation and part of speech tagging.Based on the UIUC question classification system for English and the existing classification system at home and abroad,according to the characteristics of Tibetan people’s division of things,and according to the characteristics of Tibetan language itself,this paper defines the definition The classification system and annotation standard of Tibetan questions are introduced.Secondly,it discusses the concept of interrogative sentence in English,Chinese and Tibetan literature,and defines the concept of Tibetan interrogative sentence by combining with Tibetan grammar theory,the structural characteristics of Tibetan interrogative sentence and the needs of Tibetan natural language processing.This paper sums up interrogative markers from a large number of Tibetan text corpus,and then classifies them one by one according to their word formation characteristics and semantic types.In this paper,interrogative markers are divided into interrogative pronouns,interrogative auxiliary words and interrogative structures for detailed description.Finally,this paper introduces the classification of English,Chinese and Tibetan interrogative sentences,and then makes a statistical study of Tibetan interrogative sentences and their structures by referring to the previous research results.The purpose is to test the correctness of the classification and induction of Tibetan syntactic structures,improve the efficiency of Tibetan syntactic analysis,and speed up the construction process of Tibetan syntactic treebank.In a word,the research of Tibetan interrogative sentences provides support for Tibetan syntactic analysis and treebank construction,and has obvious practical significance and important theoretical significance for Tibetan question answering system,machine translation,search engine,text classification and other application fields.