论文部分内容阅读
信息快速发展的今日,计算机语言学和信息处理是一个计算机科学,语言学,文字学,数学,逻辑学等多个学科的交叉的一门新研究领域。自然语言处理并不是一般地研究自然语言,而在于研制能有效地实现自然语言通信的计算机系统,特别是其中的软件系统。因而它是计算机科学的一部分。它研究能实现人与计算机之间用自然语言进行有效通信的各种理论和方法。维吾尔语是粘着性语言,其形态变化比较丰富。短语研究目前以做人工短语划分状态。因为句子中所含的短语种类多。可以这么说:句子是短语和句子附加成分做成的。分析句子中的每一个类的短语是有难度,需要大量的工作。通过这次以动词短语作为主体研究,先简单句当中的把动词短语分出来。首先用人工建一个句子附加成分的数据库表。通过数据库表来分出句子中的动词部分和谓语部分。这次工作,虽然研究范围不大,不全面,可是处理好句子的重要组成部分的谓语是一次很有意义的研究,它可以决定组成句子的其他成分在句子中的位置。
Today’s rapid development of information, computer linguistics and information processing is a computer science, linguistics, philology, mathematics, logic and other disciplines of a cross of a new field of study. Natural language processing is not a general study of natural language, but rather the development of computer systems that enable efficient natural language communication, especially the software systems involved. It is therefore a part of computer science. It studies various theories and methods that enable effective communication between humans and computers in natural language. Uyghur language is a sticky language, its morphology is rich. Phrase studies currently use artificial phrases to divide states. Because the phrase contains many types of phrases. So to speak: Sentences are made of phrases and sentence attachments. Analyzing phrases in each of the classes in a sentence is difficult and requires a lot of work. Through the study of the verb phrase as the main subject, the verb phrase is first divided into simple sentences. First, use artificial to build a sentence additional components of the database table. Through the database table to separate sentences in the verb part and the predicate part. Although this research is not extensive and incomplete, the predicate that is an important part of the sentence is a meaningful one. It can determine the position of the other components that make up the sentence in the sentence.