Natural reference to objects in a visual domain

Authors:
Margaret Mitchell;Kees van Deemter;Ehud Reiter
Affiliations:
University of Aberdeen, Scotland, U.K.;University of Aberdeen, Scotland, U.K.;University of Aberdeen, Scotland, U.K.
Venue:
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Year:
2010

Citing 8
Cited 1

Image and brain: the resolution of the imagery debate

Image and brain: the resolution of the imagery debate
Collaborating on referring expressions

Computational Linguistics
Graph-based generation of referring expressions

Computational Linguistics
The pragmatics of referring and the modality of communication

Computational Linguistics
Dynamically structuring, updating and interrelating representations of visual and linguistic discourse context

Artificial Intelligence - Special volume on connecting language to the world
Building a semantically transparent corpus for the generation of referring expressions

INLG '06 Proceedings of the Fourth International Natural Language Generation Conference
Referring expressions as formulas of description logic

INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
The use of spatial relations in referring expression generation

INLG '08 Proceedings of the Fifth International Natural Language Generation Conference

Two approaches for generating size modifiers

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses the basic structures necessary for the generation of reference to objects in a visual scene. We construct a study designed to elicit naturalistic referring expressions to relatively complex objects, and find aspects of reference that have not been accounted for in work on Referring Expression Generation (REG). This includes reference to object parts, size comparisons without crisp measurements, and the use of analogies. By drawing on research in cognitive science, neurophysiology, and psycholinguistics, we begin developing the input structure and background knowledge necessary for an algorithm capable of generating the kinds of reference we observe.