Body movement construction based on distributionally represented size image

This study proposes a method of generating body gestures from distributed representations of words. In the method, the size image for words is computed based on the axis whose poles correspond to "small" and "large" word images. In addition, the size image of the words is physically implemented as robot gestures. The proposed methods were evaluated by two online surveys. Summarizing the results, the authors claim the potential of developing artifacts exchanging qualitative and quantitative aspects of word representations.