Paper: Evaluation of a System for Noun Concepts Acquisition from Utterances about Images (SINCA) Using Daily Conversation Data

ACL ID N09-2017
Title Evaluation of a System for Noun Concepts Acquisition from Utterances about Images (SINCA) Using Daily Conversation Data
Venue Human Language Technologies
Session Short Paper
Year 2009
Authors

For a robot working in an open environment, a task-oriented language capability will not be sufficient. In order to adapt to the en- vironment, such a robot will have to learn language dynamically. We developed a Sys- tem for Noun Concepts Acquisition from ut- terances about Images, SINCA in short. It is a language acquisition system without knowl- edge of grammar and vocabulary, which learns noun concepts from user utterances. We recorded a video of a child’s daily life to collect dialogue data that was spoken to and around him. The child is a member of a fam- ily consisting of the parents and his sister. We evaluated the performance of SINCA using the collected data. In this paper, we describe the algorithms of SINCA and an evaluation experiment. We work on Japanese language acquisitio...