Computer simulation of mental image processing in natural language understanding by human

摘要

The terminology `natural language' surely reminds most people of any ordinary human language that they use to communicate with each other, but as well it alludes to the most convenient way by which ordinary non-expert people can intuitively interact with artifacts such as robots. Therefore, without any doubt, the technology of Natural Language Understanding (NLU) plays a key role at such intuitive human-machine interaction. In this paper, focusing on spatiotemporal (or 4D) language, NLU by human as mental image processing is attempted to simulate so that robots can understand texts in the same way as people. The proposed methodology is quite distinguished from conventional ones and shows a potential good enough to be a very powerful means for realizing awareness in computer and its understanding.