西安电子科技大学 硕士学位论文 基于数据库的自然语言查询技术与实现 姓名：杨伟 申请学位级别：硕士 专业：计算机应用技术 指导教师：刘志镜 20100101 ? ? ? ? ? ? ? ?(HMM)? ? ? ? ? ? ? ? ? ? ? ? Abstract Database technology becomes increasingly sophisticated, and has been applied to all walks of life, but it only allows professional to operate. Natural language, as a major mode of information expression, combined with database information query, has great theoretical and practical value, which makes more and more laypeople use the convenient method to access the information needed. The purpose of this paper is to research natural language query technology based on database. Firstly we introduce the features of natural language query interface on database: the query statement with certain laws to follow meets specific grammar rules, so it is achievable, and then part of speech tagging based on HMM, named entity recognition method based on role tagging and other related theories are discussed, which makes word segmentation more accurate. The design of repository is of great essential, and different types of repository are the basis of the lexical and syntactic analysis. Chinese word segmentation is a necessary step in processing, we adopt a two-way maximum matching method to process the chinese word, and eliminate ambiguity to some extent. For some unknown word, the system has done accordingly. Next we discuss the syntactic analysis combined with the features of query statement, mainly about the query target and condition, the target word has a variety of circumstances, this paper has made a detailed discussion. Considering the queries of general people, we research different types of target phrases and various types of conditions in depth. A Natural Language Query System is designed and implemented in the community personnel files database and LIAN Company Information Database with the knowledge and technologies mentioned above, and it achieves the expectant goal. In the final part, the conclusion and prospect about this system is proposed. Keyword: Natural Language Processing (NLP) Lexical analysis Syntactic analysis Repository ? ? ? ? ? ? ? ? ? ? ? ? ? ?(? ?) ? ? ? ? ?1 ? ? 1.1 ? ? ? ?2007BAH08B02? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? 1.2 ? ? ?1? 20?60?BASEBALL?2? ? ?BASEBAL ? ?20?70? ? 2? ?LUNAR3,4?LUNAR? ? ? ? ? ? ? ? ?LIFFER? ?5?LADDER6? ? ? SQL SERVER?English Query? ? ? ? ? ?80?90? (1) ?EAAD?7?ER? ? ? (2) ?WTCDIS?8? ? ? ? (3) ?NCHIQL9,10? ?