Study On The Automatic Chinese Word Segmentation With Chinese Names Recognation Function

With the rapid development of information technology, the Chinese information processing technology has already permeated through each field of computer application. The word processing platform technology is the intermediate link of Chinese information processing. It is the key link to connect character processing platform and sentence processing platform, of which the most difficult problem is the word segmentation problem. Chinese automatic word segmentation is the first step of automatic analysis of Chinese text, and the foundation of word processing platform. The development of Chinese word segmentation technology is influencing the development of the Chinese information processing technology directly.The paper depicts the knowledge of automatic Chinese word segmentation in detail. It introduces the concept and current research and application situation at home and abroad of automatic Chinese word segmentation. The paper summarizes and describes the theories, methods, evaluating standards and basic workflow of automatic Chinese word segmentation. Especially the researching emphasis is on the techniques and algorithms of ambiguities recognition and processing as well as Chinese names recognition, and put forward the relevant advanced algorithms.This text uses the reverse directional maximum matching method and improved maximum matching method to get data from the ambiguitious fields. This text also makes some improvement in the ambiguities processes. It combines statistics and rule methods together, and makes use of some word segmentation methods based on the regularity and the most probability method to reduce the ambiguitious fields. Simultaneously by combining statistics and rule methods together, it makes experiments on Chinese names recognition, realizes the algorithm of automatic Chinese word segmentation with Chinese names recognition function. Through the experimental data, this algorithm can basically deal with practical problem of Chinese information processing.