Research Of Automatic EEC Question Answering System Based On Dynamic Knowledge Base

As Internet popularizes, more and more information are available online, providing a huge amount of resources for people. However, with the overwhelming information, people find it very difficult to find the information they need quickly and accurately. There are some search engines that can help people to search for needed information, but they are far from being satisfactory. Question answering (QA) technology is developed to meet people's demand. The inputs of search engines are combinations of keywords, while QA systems enable users to input a question in natural languages. The outputs of search engines are some related web pages, while QA systems can give users concise and accurate answers. By using QA systems, users can find the information they need conveniently, quickly and accurately.The author develops about EEC(entrance examination for the college) asking an automatic question answer system based on dynamic knowledge database and faced on the consultation of college entrance exam that enhances the functions of existing search engines, so that they support natural language question answering. In this paper, through describing the flow and design thinking of our system firstly, give the analyze and research of every part of QA systems deeply. Question-based Object-oriented Knowledge Representation method is the main method used to construct knowledge base in this paper. In question analysis module, a rule-based method for question classification is used. In the question participle module, arithmetic of MM has been improved and importing question clustering in answer agent module. In the answer extraction module, one improved arithmetic of sentence similarity computation and knowledge illation have been used. Analyze the test results of this system and give the conclusion and introduce the further work in the end.The main work of this paper is as the following:1. Designing and implementing the automatic question answer system based on dynamic knowledge database and faced on the consultation of college entrance exam2. Using the technology of object-oriented knowledge representation into automatic question answer3. Improving the arithmetic of MM in the question participle module4. Improving the arithmetic of Bayesian in the question clustering module5. Improving the arithmetic of similarity and using simple knowledge illation into the answer extraction module...