Automatic Acquisition Of Domain Terms

Automatic Acquisition of Domain Terms is an important research issue in natural language processing (NLP). By the extension of domain application in NLP, it becomes more and more urgent to get the domain knowledge. The research proves that it can get the better effect when inducts the domain knowledge to many technology of information processing, such as information retrieval, information extraction, data mining. But this approach depends on a huge domain database on high degree. Domain database is mainly constituted by manpower, and it costs immensely and evolves slowly. How to automatic acquisition of domain terms and find new domain terms in time show theoretical and real significance of keeping up with the pace of world in this domain.Nowadays, research on acquisition Chinese domain terms focuses on analyzing corpus, but seldom in automatic acquisition of domain terms. The acquisition of domain terms usually rely on foreign research achievement based on western languages, but it is not quite suitable for research based on Chinese, so to develop suitable way for acquisition Chinese domain terms is very important for Chinese term standardization as well as Chinese Information Processing.Aiming at the present situation, this paper pays attention to the research of automatic acquisition domain terms techniques, the main work are as follows:1. Analysis and compare all kinds of automatic acquisition domain terms models2. Propose an automatic acquisition domain terms model based on CBC clustering approach, many disadvantages are avoided in our model.3. Propose the method to appraise term and modify Cosine Coefficient to calculate mutual information. Then design the key part by using this algorithm.