Logical Model of Human Mental Image Processing in Spatiotemporal Language Understanding

Abstract: Natural language is the most convenient means that people use to communicate with each other conventionally. This is also the case for casual and intuitive interaction between ordinary non-expert people and artifacts such as robots. Therefore, it is doubtless that the technology of Natural Language Understanding (NLU) should play a key role at such scenes of humans and machines. In this paper, focusing on spatiotemporal (or 4D) language, NLU by human based on mental image 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 good potential for providing robots with an NLU mechanism guided by humanlike awareness control based on mental image.