A semantic relation learning device (1) is provided with: a negative example data creation unit (12) that creates a plurality of negative example data pairs by combining language data items respectively constituting a plurality of positive example data pairs; a feature amount extraction unit (13) that extracts feature amounts from language data items respectively constituting the negative example data pairs; a similarity calculation unit (14) that calculates similarity between the feature amounts in the negative example data pairs; a learning negative example data creation unit (15) that, by classifying, on the basis of the similarity, the plurality of negative example data pairs into a plurality of predetermined similarity ranges, creates a plurality of learning negative example data sets respectively corresponding to the plurality of similarity ranges; a learning data set selection unit (17) that, in order following a selection schedule determined in advance on the basis of the plurality of similarity ranges, selects any one of the plurality of learning negative example data sets; and a learning processing unit (18) that performs a machine learning process by using the selected learning negative example data set and the plurality of positive example data pairs.
展开▼