MEANING-CENTRIC FRAMEWORK FOR NATURAL TEXT/SCENE UNDERSTANDING BY ROBOTS

Abstract

In the past fifty years, efforts in classical AI have focussed on computerizing human intelligence. Naturally, computerized human intelligence is not a proof of machine or robot intelligence because the programs underlying computerized human intelligence are still made by humans. So far, there is no computer nor robot which is creative enough to master its own language and to compose a text expressing its intentions. Thus, it is time to shift our research focus from computerizing human intelligence to developing machine intelligence. A first and necessary step towards this goal is to make machines or robots learn, manipulate, understand and create both elementary and composite meanings encoded in a natural language such as English. Elementary and composite meanings could be acquired through both sample texts and images. Hence, we propose a learning-synthesis-analysis framework which aims to enable a robot, or computer, to understand and convey meaning through texts or images. The main contribution of this paper is to lay out a sound foundation on which interdisciplinary research could effectively progress toward the development of machines or robots that understand meaning through texts or images.