Abstract
In case of a robot working in an open environment, the task-oriented language ability will not be sufficient. To adapt to the environment, it is necessary to acquire language dynamically. We developed a System for Noun Concepts Acquisition from utterances about Images, called SINCA in short. It is a language acquisition system without knowledge of grammar and vocabulary, which learns noun concepts from a user's input.
We collected dialogue data from parents and their children. We evaluated the performance of SINCA with the collected data.
In this paper, we describe an algorithm of SINCA and an evaluation experiment.
