Computational generation of referring expressions: a survey

Emiel Krahmer, Kees van Deemter

Research output: Contribution to journalArticle

117 Citations (Scopus)

Abstract

This article offers a survey of computational research on referring expressions generation (REG). It introduces the REG problem and describes early work in this area, discussing what basic assumptions lie behind it, and showing how its remit has widened in recent years. We discuss computational frameworks underlying REG, and demonstrate a recent trend that seeks to link up REG algorithms with well-established Knowledge Representation traditions. Considerable attention is given to recent efforts at evaluating REG algorithms and the lessons that they allow us to learn. The article concludes with a discussion of the way forward in REG, focussing on references in larger and more realistic settings.
Original languageEnglish
Pages (from-to)173-218
Number of pages46
JournalComputational Linguistics
Volume38
Issue number1
Early online date20 Jan 2012
DOIs
Publication statusPublished - Mar 2012

Fingerprint

Knowledge representation
Referring Expressions
Computational
trend

Keywords

  • survey
  • generaton of referring expressions

Cite this

Computational generation of referring expressions: a survey. / Krahmer, Emiel; van Deemter, Kees.

In: Computational Linguistics, Vol. 38, No. 1, 03.2012, p. 173-218.

Research output: Contribution to journalArticle

Krahmer, Emiel ; van Deemter, Kees. / Computational generation of referring expressions: a survey. In: Computational Linguistics. 2012 ; Vol. 38, No. 1. pp. 173-218.
@article{042040852df8464dbe31b385c31e3d69,
title = "Computational generation of referring expressions: a survey",
abstract = "This article offers a survey of computational research on referring expressions generation (REG). It introduces the REG problem and describes early work in this area, discussing what basic assumptions lie behind it, and showing how its remit has widened in recent years. We discuss computational frameworks underlying REG, and demonstrate a recent trend that seeks to link up REG algorithms with well-established Knowledge Representation traditions. Considerable attention is given to recent efforts at evaluating REG algorithms and the lessons that they allow us to learn. The article concludes with a discussion of the way forward in REG, focussing on references in larger and more realistic settings.",
keywords = "survey, generaton of referring expressions",
author = "Emiel Krahmer and {van Deemter}, Kees",
year = "2012",
month = "3",
doi = "10.1162/COLI_a_00088",
language = "English",
volume = "38",
pages = "173--218",
journal = "Computational Linguistics",
issn = "0891-2017",
publisher = "MIT Press Journals",
number = "1",

}

TY - JOUR

T1 - Computational generation of referring expressions: a survey

AU - Krahmer, Emiel

AU - van Deemter, Kees

PY - 2012/3

Y1 - 2012/3

N2 - This article offers a survey of computational research on referring expressions generation (REG). It introduces the REG problem and describes early work in this area, discussing what basic assumptions lie behind it, and showing how its remit has widened in recent years. We discuss computational frameworks underlying REG, and demonstrate a recent trend that seeks to link up REG algorithms with well-established Knowledge Representation traditions. Considerable attention is given to recent efforts at evaluating REG algorithms and the lessons that they allow us to learn. The article concludes with a discussion of the way forward in REG, focussing on references in larger and more realistic settings.

AB - This article offers a survey of computational research on referring expressions generation (REG). It introduces the REG problem and describes early work in this area, discussing what basic assumptions lie behind it, and showing how its remit has widened in recent years. We discuss computational frameworks underlying REG, and demonstrate a recent trend that seeks to link up REG algorithms with well-established Knowledge Representation traditions. Considerable attention is given to recent efforts at evaluating REG algorithms and the lessons that they allow us to learn. The article concludes with a discussion of the way forward in REG, focussing on references in larger and more realistic settings.

KW - survey

KW - generaton of referring expressions

U2 - 10.1162/COLI_a_00088

DO - 10.1162/COLI_a_00088

M3 - Article

VL - 38

SP - 173

EP - 218

JO - Computational Linguistics

JF - Computational Linguistics

SN - 0891-2017

IS - 1

ER -