Natural reference to objects in a visual domain

Margaret Mitchell; Kees van Deemter; Ehud Reiter

Natural reference to objects in a visual domain

Margaret Mitchell, Kees van Deemter, Ehud Reiter

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

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 and psycholinguistics, we begin developing the input structure and background knowledge necessary for an algorithm capable of generating the kinds of reference we observe.

Original language	English
Title of host publication	INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland
Editors	John Kelleher, Brian Macnamee, Ielka van der Sluis, Anja Belz, Albert Gatt, Alexander Koller
Place of Publication	Stroudsburg, PA, USA
Publisher	Association for Computational Linguistics
Pages	95-104
Number of pages	10
Publication status	Published - 2010

Keywords

generation of referring expressions
elicitation experiment
spoken monologue

Access to Document

http://homepages.abdn.ac.uk/k.vdeemter/pages/INLG2010-Meg.pdf

Cite this

Mitchell, M., van Deemter, K., & Reiter, E. (2010). Natural reference to objects in a visual domain. In J. Kelleher, B. Macnamee, I. van der Sluis, A. Belz, A. Gatt, & A. Koller (Eds.), INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland (pp. 95-104). Association for Computational Linguistics. http://homepages.abdn.ac.uk/k.vdeemter/pages/INLG2010-Meg.pdf

Natural reference to objects in a visual domain. / Mitchell, Margaret; van Deemter, Kees; Reiter, Ehud.
INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland. ed. / John Kelleher; Brian Macnamee; Ielka van der Sluis; Anja Belz; Albert Gatt; Alexander Koller. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010. p. 95-104.

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Mitchell, M, van Deemter, K & Reiter, E 2010, Natural reference to objects in a visual domain. in J Kelleher, B Macnamee, I van der Sluis, A Belz, A Gatt & A Koller (eds), INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland. Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 95-104. <http://homepages.abdn.ac.uk/k.vdeemter/pages/INLG2010-Meg.pdf>

Mitchell M, van Deemter K, Reiter E. Natural reference to objects in a visual domain. In Kelleher J, Macnamee B, van der Sluis I, Belz A, Gatt A, Koller A, editors, INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland. Stroudsburg, PA, USA: Association for Computational Linguistics. 2010. p. 95-104

Mitchell, Margaret ; van Deemter, Kees ; Reiter, Ehud. / Natural reference to objects in a visual domain. INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland. editor / John Kelleher ; Brian Macnamee ; Ielka van der Sluis ; Anja Belz ; Albert Gatt ; Alexander Koller. Stroudsburg, PA, USA : Association for Computational Linguistics, 2010. pp. 95-104

@inproceedings{47e3e83ce7324c81bf726192421dcbce,

title = "Natural reference to objects in a visual domain",

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 and psycholinguistics, we begin developing the input structure and background knowledge necessary for an algorithm capable of generating the kinds of reference we observe.",

keywords = "generation of referring expressions , elicitation experiment, spoken monologue",

author = "Margaret Mitchell and {van Deemter}, Kees and Ehud Reiter",

year = "2010",

language = "English",

pages = "95--104",

editor = "Kelleher, {John } and Macnamee, {Brian } and {van der Sluis}, Ielka and Anja Belz and Albert Gatt and Alexander Koller",

booktitle = "INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - Natural reference to objects in a visual domain

AU - Mitchell, Margaret

AU - van Deemter, Kees

AU - Reiter, Ehud

PY - 2010

Y1 - 2010

N2 - 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 and psycholinguistics, we begin developing the input structure and background knowledge necessary for an algorithm capable of generating the kinds of reference we observe.

AB - 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 and psycholinguistics, we begin developing the input structure and background knowledge necessary for an algorithm capable of generating the kinds of reference we observe.

KW - generation of referring expressions

KW - elicitation experiment

KW - spoken monologue

M3 - Published conference contribution

SP - 95

EP - 104

BT - INLG 2010 - Proceedings of the Sixth International Natural Language Generation Conference, July 7-9, 2010, Trim, Co. Meath, Ireland

A2 - Kelleher, John

A2 - Macnamee, Brian

A2 - van der Sluis, Ielka

A2 - Belz, Anja

A2 - Gatt, Albert

A2 - Koller, Alexander

PB - Association for Computational Linguistics

CY - Stroudsburg, PA, USA

ER -