This article discusses face translation (FT), which replaces the user's face with an expression by a different synthetic face, such as the face of an avatar or a cartoon character, with the same expression. In order to realize FT, we have to establish a criterion to define which expression on the synthetic face is the "same" expression as the user wears on his/her face. Different from previous work, it is proposed in this article to adopt the user's subjective viewpoint for this criterion. The user's viewpoint is acquired online through the interaction with the user. When the user is not satisfied with the synthetic facial expression given as the result of FT by the system, the user corrects it by a graphical user interface (GUI). The system obtains examples of the FT from the user's subjective viewpoint every time the user corrects the results of translation. With increase of examples, the result of FT by the system gradually comes to reflect the user's subjective viewpoint, so that the user does not need to correct the result.