Learning Communicative Meanings of Utterances by Robots
This paper describes a computational mechanism that enables a robot to return suitable utterances to a human or perform actions by learning the meanings of interrogative words, such as “what” and “which.” Previous studies of language acquisition by robots have proposed methods to learn words, such as “box” and “blue,” that indicate objects or events in the world. However, the robots could not learn and understand interrogative words by those methods because the words do not directly indicate objects or events. The meanings of those words are grounded in communication and stimulate specific responses by a listener. These are called communicative meanings. Our proposed method learns the relationship between human utterances and robot responses that have communicative meanings on the basis of a graphical model of the human-robot interaction.
KeywordsLanguage Acquisition Human-Robot Interaction Machine Learning
Unable to display preview. Download preview PDF.
- 1.Regier, T.: The Human Semantic Potential: Spatial Language and Constrained Connectionism. MIT Press, Cambridge (1996)Google Scholar
- 2.Akaho, S., Hasegawa, O., Yoshimura, T., Asoh, H., Hayamizu, S.: Concept acquisition from multiple information sources by the EM algorithm. IEICE Trans. J80-A(9), 1546–1553 (1997)Google Scholar
- 3.Steels, L., Kaplan, K.: AIBO’s first words: the social learning of language and meaning. Evolution of Communication 4(1), 3–32 (2001)Google Scholar
- 5.Yu, C., Ballard, D.: On the Integration of Grounding Language and Learning Objects. In: Proc. 19th National Conference on Artificial Intelligence (AAAI), pp. 488–494 (2004)Google Scholar
- 6.Iwahashi, N.: Robots That Learn Language: A Developmental Approach to Situated Human-Robot Conversations. In: Sankar, N. (ed.) Human-Robot Interaction, pp. 95–118. I-Tech Education and Publishing (2007)Google Scholar