Object-oriented Semantic Graph Based Natural Question Generation
Jiyoun Moon,Beom-Hee Lee,Jiyoun Moon,Beom-Hee Lee
Generating a natural question can enable autonomous robots to propose problems according to their surroundings. However, recent studies on question generation rarely consider semantic graph mapping, which is widely used to understand environments. In this paper, we introduce a method to generate natural questions using object-oriented semantic graphs. First, a graph convolutional network extracts ...
