Wenxin Li’s research while affiliated with Nanjing University of Aeronautics and Astronautics and other places

In order to implement automatic inference, this paper proposes a visual semantic-relations detecting method (VSRDM) based on WordNet. WordNet is an excellent relational dictionary, but it lacks deep semantic topology function because of its index-based text storage structure. As a graphical database, Neo4J provides visualization of its internal data. Since the abstract data structure in WordNet matches Neo4J’s ternary storage structure, it is very suitable to map WordNet completely with Neo4J graph instance. This paper studies how to fully describe WordNet in Neo4J through a ternary structure. Neo4J stores the data as graphs (nodes and edges) and provides certain native graph algorithms to search the data. The speed of matching query between nodes is varying linearly with the number of nodes, so the efficiency of basic operation is guaranteed. With the help of Neo4J, VSRDM works as a semantic dictionary providing relationships matching, reasoning auxiliary and other functions.

In the big data era, data and information processing is a common concern of diverse fields. To achieve the two keys “efficiency” and “intelligence” to the processing process, it’s necessary to search, define and build the potential links among heterogeneous data. Focusing on this issue, this paper proposes a knowledge-driven method to calculate the semantic similarity between (bilingual English-Chinese) words. This method is built on the knowledge base “HowNet”, which defines and maintains the “atom taxonomy tree” and the “semantic dictionary” - a network of knowledge system describing the relationships between word concepts and attributes of the concepts. Compared to other knowledge bases, HowNet pays more attention to the connections between words based on concepts. Besides, this method is more complete in the analysis of concepts and more convenient in calculation methods. The non-relational database MongoDB is employed to improve the efficiency and fully use the rich knowledge maintained in HowNet. Considering both the structure of HowNet and characteristics of MongoDB, a certain number of equations are defined to calculate the semantic similarity.