A synonym dictionary with high precision is made and a synonym dictionary is automatically generated from the text. Morphological analysis is performed on the text, and the text is divided into a plurality of words to obtain morpheme-interpreted text. Topic classification is performed on the morpheme-interpreted text, and at least one topic word belonging to each topic is selected from a plurality of words, and a reference word characterizing each topic is extracted from at least one topic word. A plurality of words are multidimensionally vectorized, and a plurality of vectors representing each of the plurality of words are obtained. At least one similar word is selected from a plurality of words. At least one similar word is selected such that the degree of similarity between the vector representing the reference word and the vector representing each similar word of the at least one similar word is higher than a set criterion. A synonym dictionary is created in which at least a part of at least one synonym is registered.
展开▼