SEMANTIC SYNTAX TREE KERNEL-BASED PROCESSING SYSTEM AND METHOD FOR AUTOMATICALLY EXTRACTING SEMANTIC CORRELATIONS BETWEEN SCIENTIFIC AND TECHNOLOGICAL CORE ENTITIES

摘要

The present disclosure relates to a semantic parse tree kernel-based processing system and method of automatically extracting a semantic correlation between scientific and technological core entities. The method includes parsing syntaxes, part-of-speech information, and base chunk information on input sentences; extracting a relation of the syntaxes of the input sentences by performing a parse tree pruning based on the parsed syntaxes, part-of-speech information, and base chunk information; and extracting a similarity of the syntaxes of the input sentences by calculating a syntactic similarity, a lexical semantic similarity, and a semantic parse tree kernel of the syntaxes of the input sentences based on the extracted relations of the syntaxes of the input sentences, thereby more accurately calculating the similarity between two sentences.