Computer Processing Of Natural Language Model

NLP, Natural Language Processing, is a cross-fields science. Many scientist from computer science, linguistics, mathematics and many other fields join its researching. Its functions develop from main in numeric computing to data information processing attached importance to numeric computing. The NLP is how to make computer understanding and create the words in people's nature language, i.e Chinese, English, understand the nature language, and communicate with people in nature language, i.e answer the people's question. Its goal is building up a osculation and friendly relationship between people and computer and using it to efficiently communication.By now, the researchment of NLP is far away from our demand. We are engaged in making computer comprehend nature language information correctly. Main methods of NLP include statistics based on language information corpus and parsing language information based on rules. Both of the methods make some achievement, but both of them must need a reliable natur language denotation to make computer comprehend language correctly and improve their development.This dissertation mainly discuss the knowledge repository and the article knowledge extracting based on it as well as describe a brief NLP frame. The knowledge repository is the natur language denotation system. We use the OOP programe plus database to design it. In detail, we use OOP to descibe the concept sort of nature language and database to restore the relation of word and our program. So that, computer can parse the collection of some objects that can descibe the meaning of the word rather othan the meaningless codes of nature language words. This knowledge repository can satisfy our resent requirment. We also attempt to make the article knowledge extracting based on this knowledge repository. The extracted result is a set of objects. We can use it to answer some simple questions of this article. At last, dissertation points out the draw back of our program and submits several possible solutions.