Generation of relative referring expressions based on perceptual grouping

Authors:
Kotaro Funakoshi;Satoru Watanabe;Naoko Kuriyama;Takenobu Tokunaga
Affiliations:
Tokyo Institute of Technology, Meguro Ôokayama, Tokyo, Japan;Tokyo Institute of Technology, Meguro Ôokayama, Tokyo, Japan;Tokyo Institute of Technology, Meguro Ôokayama, Tokyo, Japan;Tokyo Institute of Technology, Meguro Ôokayama, Tokyo, Japan
Venue:
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Year:
2004

Citing 8
Cited 2

Planning english referring expressions

Artificial Intelligence - Lecture notes in computer science 178
Collaborating on referring expressions

Computational Linguistics
Language and Spatial Cognition

Language and Spatial Cognition
Character-Based Interactive Storytelling

IEEE Intelligent Systems
Generating referring expressions: boolean extensions of the incremental algorithm

Computational Linguistics
Graph-based generation of referring expressions

Computational Linguistics
Generating referring expressions involving relations

EACL '91 Proceedings of the fifth conference on European chapter of the Association for Computational Linguistics
An algorithm for generating referential descriptions with flexible interfaces

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics

Anchor-progression in spatially situated discourse: a production experiment

INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Midge: generating image descriptions from computer vision detections

EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Past work of generating referring expressions mainly utilized attributes of objects and binary relations between 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 method utilizing the perceptual groups of objects and n-ary relations among them. 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.