Generating Referring Expressions based-on Perceptual Grouping

DOI Web Site Web Site 2 Citations 17 References
  • FUNAKOSHI KOTARO
    Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
  • WATANABE SATORU
    Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
  • KURIYAMA NAOKO
    Department of Human System Science, Graduate School of Decision Science and Technology, Tokyo Institute of Technology
  • TOKUNAGA TAKENOBU
    Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology

Bibliographic Information

Other Title
  • 知覚的群化に基づく参照表現の生成
  • チカクテキグンカ ニ モトヅク サンショウ ヒョウゲン ノ セイセイ

Search this article

Description

Past work of generating referring expressions mainly utilized attributes of objects and binary relations between objects to distinguish the referent from other objects. However, such an approach does not work well when there is no distinctive attribute among objects.To overcome this limitation, this paper proposes a novel generation method utilizing the perceptual groups of objects and n-ary relations among them. With the proposed method, an expression like “the rightmost ball in the left cluster of three balls” can be generated.The key is to identify groups of objects that are naturally recognized by humans.We conducted psychological experiments with 42 subjects to collect referring expressions in such situations, and built a generation algorithm based on the results.The evaluation using another 23 subjects showed that the proposed method could effectively generate proper referring expressions.

Journal

Citations (2)*help

See more

References(17)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top