主観的な階層クラスタリングにおける特徴量ごとの重みを求める情報処理装置、方法、およびプログラム

摘要

To learn the weight of each physical feature so that hierarchical clustering reflecting the degree of subjective similarity can be performed. An information processing apparatus of the present invention acquires multiple pieces of content separated in a set of three pieces (hereinafter referred to as a triplet) together with label information as training data, the label information indicating a pair specified by a user as having the highest degree of similarity among three contents of the triplet. The information processing apparatus executes hierarchical clustering using a feature vector of each piece of content of the training data and the weight of each feature to determine the hierarchical structure of the training data. The information processing apparatus updates the weight of each feature so that the degree of agreement between a pair combined first as being the same clusters among three contents of the triplet in a determined hierarchical structure and a pair indicated by label information corresponding to the triplet increases.