Generating Easy References: the case of document deixis.

Ivandre Paraboni; Kees van Deemter

Generating Easy References: the case of document deixis.

Ivandre Paraboni, Kees van Deemter

Computing Science

University of Brighton

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

3 Downloads (Pure)

Abstract

This paper argues that algorithms for the
generation of referring expressions should
aim to make it easy for hearers and readers
to find the referent of the expressions that
are generated. To illustrate this claim, an
algorithm is described for the generation
of expressions that refer across a hierarchically ordered domain, and which takes
search effort into account by adding logically redundant information. To support
the ideas underlying the algorithm, a psycholinguistic experiment is presented that
confirms readers’ preference for the generated, logically redundant expressions
over non-redundant alternatives.

Original language	English
Title of host publication	Proceedings of Second International Natural Language Generation Conference (INLG-2002)
Editors	Kathleen McKeown
Publisher	Association for Computational Linguistics (ACL)
Pages	113-119
Number of pages	7
Publication status	Published - 2002
Event	2nd International Natural Language Generation Conference - Harriman, United States Duration: 1 Jul 2002 → 3 Jul 2002 https://aclanthology.org/volumes/W02-21/

Conference

Conference	2nd International Natural Language Generation Conference
Abbreviated title	INGL 2002
Country/Territory	United States
City	Harriman
Period	1/07/02 → 3/07/02
Internet address	https://aclanthology.org/volumes/W02-21/

Bibliographical note

This work is part of an ongoing PhD project of the first author and it has been supported by the CNPq, the Brazilian Research Council.

Keywords

Generation of Referring Expressions

Access to Document

Paraboni_etal_ACL_Generating_Easy_References_VoR
Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. https://creativecommons.org/licenses/by-nc-sa/3.0/
Final published version, 85 KBLicence: CC BY-NC-SA

https://aclanthology.org/W02-2115/Licence: CC BY-NC-SA

Cite this

Generating Easy References: the case of document deixis. / Paraboni, Ivandre; van Deemter, Kees.
Proceedings of Second International Natural Language Generation Conference (INLG-2002). ed. / Kathleen McKeown. Association for Computational Linguistics (ACL), 2002. p. 113-119.

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

Paraboni, I & van Deemter, K 2002, Generating Easy References: the case of document deixis. in K McKeown (ed.), Proceedings of Second International Natural Language Generation Conference (INLG-2002). Association for Computational Linguistics (ACL), pp. 113-119, 2nd International Natural Language Generation Conference, Harriman, New York, United States, 1/07/02. <https://aclanthology.org/W02-2115/>

@inproceedings{9c6bd6d882eb4bfdb9d674a41d0da7a2,

title = "Generating Easy References: the case of document deixis.",

abstract = "This paper argues that algorithms for thegeneration of referring expressions shouldaim to make it easy for hearers and readersto find the referent of the expressions thatare generated. To illustrate this claim, analgorithm is described for the generationof expressions that refer across a hierarchically ordered domain, and which takessearch effort into account by adding logically redundant information. To supportthe ideas underlying the algorithm, a psycholinguistic experiment is presented thatconfirms readers{\textquoteright} preference for the generated, logically redundant expressionsover non-redundant alternatives.",

keywords = "Generation of Referring Expressions",

author = "Ivandre Paraboni and {van Deemter}, Kees",

note = "This work is part of an ongoing PhD project of the first author and it has been supported by the CNPq, the Brazilian Research Council.; 2nd International Natural Language Generation Conference, INGL 2002 ; Conference date: 01-07-2002 Through 03-07-2002",

year = "2002",

language = "English",

pages = "113--119",

editor = "Kathleen McKeown",

booktitle = "Proceedings of Second International Natural Language Generation Conference (INLG-2002)",

publisher = "Association for Computational Linguistics (ACL)",

url = "https://aclanthology.org/volumes/W02-21/",

}

TY - GEN

T1 - Generating Easy References

T2 - 2nd International Natural Language Generation Conference

AU - Paraboni, Ivandre

AU - van Deemter, Kees

N1 - This work is part of an ongoing PhD project of the first author and it has been supported by the CNPq, the Brazilian Research Council.

PY - 2002

Y1 - 2002

N2 - This paper argues that algorithms for thegeneration of referring expressions shouldaim to make it easy for hearers and readersto find the referent of the expressions thatare generated. To illustrate this claim, analgorithm is described for the generationof expressions that refer across a hierarchically ordered domain, and which takessearch effort into account by adding logically redundant information. To supportthe ideas underlying the algorithm, a psycholinguistic experiment is presented thatconfirms readers’ preference for the generated, logically redundant expressionsover non-redundant alternatives.

AB - This paper argues that algorithms for thegeneration of referring expressions shouldaim to make it easy for hearers and readersto find the referent of the expressions thatare generated. To illustrate this claim, analgorithm is described for the generationof expressions that refer across a hierarchically ordered domain, and which takessearch effort into account by adding logically redundant information. To supportthe ideas underlying the algorithm, a psycholinguistic experiment is presented thatconfirms readers’ preference for the generated, logically redundant expressionsover non-redundant alternatives.

KW - Generation of Referring Expressions

M3 - Published conference contribution

SP - 113

EP - 119

BT - Proceedings of Second International Natural Language Generation Conference (INLG-2002)

A2 - McKeown, Kathleen

PB - Association for Computational Linguistics (ACL)

Y2 - 1 July 2002 through 3 July 2002

ER -

Generating Easy References: the case of document deixis.

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this