Abstract: A non-transitory computer readable recording medium stores therein a program that causes a computer to execute a process including: acquiring a plurality of word strings relating to a target sentence; inputting each of a plurality of combined sentences for which each of the acquired word strings is combined with the target sentence, and the target sentence into a language model, generated by using a machine learning; calculating, based on a difference between each distribution of an output result when each of the combined sentences is input into the language model, confidence in output when the target sentence is input into the language model; and outputting, based on the calculated confidence, an output result when the target sentence is input into the language model.

Abstract: A non-transitory computer-readable recording medium has stored therein a vector estimating program that causes a computer to execute a process including: obtaining a first vector and second entity information, the first vector being generated by using a first model with reference to graph structure data representing a relationship of a first entity group and being obtained by using first entity information related to the first entity group, the second entity information obtained by updating the first entity information and related to the first entity group and a second entity not being included in the first entity group; generating a second model based on the first vector and information on the first entity group included in the second entity information, the second model being used for obtaining vector data from the second entity information; and estimating a second vector corresponding to the second entity by using the generated second model.

Abstract: A shortest path searching unit 121 identifies a first group by a shortest path search conducted from a start point node in a forward direction within a first distance and identifies a second group by another shortest path search conducted from an end point node in a reverse direction within a second distance. A feature graph generating unit 122 generates, when sum of a distance of a first shortest path between the start point node and a first node included in the first group and a distance of a second shortest path between the end point node and a second node included in the second group is not more than a threshold obtained by adding a specific distance to a distance of a shortest path between the start point node and the end point node, a feature graph including the first shortest path and the second shortest path.

Abstract: A learning device generates an input vector obtained by loading a distributed representation of each of words or phrases included in subject data into a common dimension and a dimension corresponding to a data class representing a role in the subject data. The learning device executes machine learning that uses the input vectors and that relates to features of the words or phrases included in the subject data.