Can computer comprehend stories like human reader?: representing situation model as interconnected frames

  • Authors:

  • Masahiro Kiyota;Jun Ohashi;Hideji Enokidu;Seiichi Komiya

  • Affiliations:

  • Graduate School of Engineering, Shibaura Institute of Technology, Tokyo, Japan;Graduate School of Engineering, Shibaura Institute of Technology, Tokyo, Japan;Shibaura Institute of Technology, Tokyo, Japan;Graduate School of Engineering, Shibaura Institute of Technology, Tokyo, Japan

  • Venue:
  • AIKED'07 Proceedings of the 6th Conference on 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases - Volume 6
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

It is assumed that the readers construct the situation model during reading a story. The situation model is the mental microworld described in the text. According to the event-indexing model, the readers monitor four conceptual dimensions of the incoming event described in a clause: characters, time, space, causality, and intentionality. They construct the situation model of each incoming event and incorporate the model into the previous model. In the present study, we proposed the procedure to represent the situation model using four kinds of frame and the referent relationship between the frames in order to develop the computer system that comprehends the story like the human readers do.