Research And Implementation Of Chinese Intelligent Question Answering System Based On Ontology

With the development of Internet, net resources became increasingly rich. However, traditional search engine exist many disadvantages. For example, it returned the web pages not the exact answers. Furthermore, it was too difficult to understand the purpose because traditional search engine which based on the keyword index did not deal with the semantic information. But the user could ask the nature language questions in the Question Answering System which returned the answers directly after analyzing and processing the questions. So it was said QA system was the new generation search engine. Recently, Ontology was paid more and more attention and got many applications in the Artificial Intelligence area. In the closed domain QA system, Ontology knowledge base could express the inner relation and framework reasonably and reduced the redundancy, which was benefit to drawing out the answers based on semantics.After analyzing the current QA system, the paper imported ontology technique into Intelligent Question Answering System, and built a domain ontology faced to bank personal business. The ontology was the information foundation of semantic understanding. Then it would improve the lacking of semantic processing in the current QA system.There were two key modules and two core resources in the IQAS design model. The one module was Linguistic Analysis; the other was Semantic Similarity Service. Firstly, when inputting a natural language question, LA took splitting word, word markup and question pattern matching, then returned Query Linguistic Block and found the corresponding question pattern. Secondly, Semantic Similarity Service mapped Query Linguistic Block into Ontology Semantic Block, which based on the domain ontology base and Hownet. The two core resources were ontology knowledge base and question pattern base. At first we built the ontology based on the feature of bank business domain, and then the pattern base was set up after analyzing common questions.When QLB was unable to map into OSB directly, IQAS would calculate the semantic similarity between source question of the user and the replaced question. If the value of the semantic similarity between them was greater than the critical value, we would consider them similar. So the answer of the replaced question was the'closest'answer. A semantic similarity algorithm based on context was brought forward, which calculated the concept similarity of parent and child ones in the ontology. The specific environment of concepts was considered fully, and the algorithm took advantage of the semantic information of concepts.The research of the paper showed that, IQAS could make full use of the semantic information of domain ontology, and it also solved the problem of lacking semantic understanding of the current QA system to some extend and had a high correctness ratio.