Parameter learning apparatus, parameter learning method, and computer readable recording medium

Abstract

An entity combination and a text representation are obtained as a first fact, and the entity combination and a related predicate are obtained as a second fact. Word distributed representations are input to a neural network, real vectors at appearance positions of entities are specified and used as distributed representations. A first score indicating a degree of establishment of the first fact is calculated based on the distributed representations and on entity distributed representations. A second score indicating a degree of establishment is calculated with respect to an entity combination and a text representation that are not the first fact. A third score indicating a degree of establishment of the second fact is calculated based on predicate distributed representations and on entity distributed representations. A fourth score indicating a degree of establishment is calculated also with respect to an entity combination and a predicate that are not the second fact. The entity distributed representations, the predicate distributed representations, or weight parameters are updated by a gradient method, so that the first score becomes higher than one of the second score and the fourth score, and the third score becomes higher than one of the second score and the fourth score.