Evaluating centering for information ordering using corpora

Nikiforos Karamanis, Chris Mellish, Massimo Poesio, Jon Oberlander

Research output: Contribution to journalArticle

12 Citations (Scopus)
4 Downloads (Pure)

Abstract

In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclusively on NOCB transitions) sets a robust baseline that cannot be outperformed by other metrics which make use of additional centering-based features. This baseline can be used for the development of both text-to-text and concept-to-text generation systems.
Original languageEnglish
Pages (from-to)29-46
Number of pages18
JournalComputational Linguistics
Volume35
Issue number1
DOIs
Publication statusPublished - Mar 2009

Fingerprint

methodology
Text Generation
coherence
Methodology
Usefulness
Centering Theory

Cite this

Evaluating centering for information ordering using corpora. / Karamanis, Nikiforos; Mellish, Chris; Poesio, Massimo; Oberlander, Jon.

In: Computational Linguistics, Vol. 35, No. 1, 03.2009, p. 29-46.

Research output: Contribution to journalArticle

Karamanis, Nikiforos ; Mellish, Chris ; Poesio, Massimo ; Oberlander, Jon. / Evaluating centering for information ordering using corpora. In: Computational Linguistics. 2009 ; Vol. 35, No. 1. pp. 29-46.
@article{67b09e4eb63b4015aa0f61fb58dbc078,
title = "Evaluating centering for information ordering using corpora",
abstract = "In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclusively on NOCB transitions) sets a robust baseline that cannot be outperformed by other metrics which make use of additional centering-based features. This baseline can be used for the development of both text-to-text and concept-to-text generation systems.",
author = "Nikiforos Karamanis and Chris Mellish and Massimo Poesio and Jon Oberlander",
note = "Many thanks to Aggeliki Dimitromanolaki, Mirella Lapata, and Regina Barzilay for their data; to David Schlangen, Ruli Manurung, James Soutter, and Le An Ha for programming solutions; and to Ruth Seal and two anonymous reviewers for their comments. Nikiforos Karamanis received support from the Greek State Scholarships Foundation (IKY) as a PhD student in Edinburgh as well as the Rapid Item Generation project and the BBSRC-funded FlySlip grant (No 38688) as a postdoc in Wolverhampton and Cambridge, respectively",
year = "2009",
month = "3",
doi = "10.1162/coli.07-036-R2-06-22",
language = "English",
volume = "35",
pages = "29--46",
journal = "Computational Linguistics",
issn = "0891-2017",
publisher = "MIT Press Journals",
number = "1",

}

TY - JOUR

T1 - Evaluating centering for information ordering using corpora

AU - Karamanis, Nikiforos

AU - Mellish, Chris

AU - Poesio, Massimo

AU - Oberlander, Jon

N1 - Many thanks to Aggeliki Dimitromanolaki, Mirella Lapata, and Regina Barzilay for their data; to David Schlangen, Ruli Manurung, James Soutter, and Le An Ha for programming solutions; and to Ruth Seal and two anonymous reviewers for their comments. Nikiforos Karamanis received support from the Greek State Scholarships Foundation (IKY) as a PhD student in Edinburgh as well as the Rapid Item Generation project and the BBSRC-funded FlySlip grant (No 38688) as a postdoc in Wolverhampton and Cambridge, respectively

PY - 2009/3

Y1 - 2009/3

N2 - In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclusively on NOCB transitions) sets a robust baseline that cannot be outperformed by other metrics which make use of additional centering-based features. This baseline can be used for the development of both text-to-text and concept-to-text generation systems.

AB - In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclusively on NOCB transitions) sets a robust baseline that cannot be outperformed by other metrics which make use of additional centering-based features. This baseline can be used for the development of both text-to-text and concept-to-text generation systems.

U2 - 10.1162/coli.07-036-R2-06-22

DO - 10.1162/coli.07-036-R2-06-22

M3 - Article

VL - 35

SP - 29

EP - 46

JO - Computational Linguistics

JF - Computational Linguistics

SN - 0891-2017

IS - 1

ER -