Semantic Similarity Computation And Application For Text Based On HNC Theory

With the development of information technology and internet, information resources are growing very fast.80%of the information resources appears in natural language text. How to get the knowledge from the big data is in urgent need of automation and intelligent processing. For example, natural language processing, text mining, intelligent retrieving and automatic answer system. Text semantic similarity computation is the key technology to the automation processing.Firstly, on the base of analysis of background and research status of text semantic similarity computation, we make it clear that the research object is unstructured free Chinese text and the research goal is to quantify the semantic similarity between two texts. Secondly, on the basic of summarizing the theories of this paper, including natural language processing, dependency theory, Hierarchical Network of Concepts(HNC) theory, information retrieval, we bring up a method for computing word semantic similarity. A new measure method based on Hierarchical Network of Concepts (HNC) theory in natural language processing is put forward to compute the semantic similarity. Based on the coding rules and the map theory included in the concept expression form in the vocabulary relation level of HNC theory, the method integrates the concept of connotation, outward features, classification and combination of symbol to calculate semantic similarity. Then, a novel measure method based on HNC theory and dependency theory in natural language processing is putting forward to compute the sentence semantic similarity. The meaning of a sentence is made up of the meanings of its individual words and the structural way the words combined, and semantic information is obtained from HNC theory, and the syntactic information is obtained through a deep parsing process. Last but not least, the method proposed in this paper was applied in user-interactive automatic answering system of the infant education. Designing and implementing system from text resources system to validity of the method.This paper aims to calculate the Chinese text semantic similarity, including word and sentence. This study can be a kind of technology and theory solutions for automation processing.