GRAPH: the costs of redundancy in referring expressions

Emiel Krahmer; Mariët Theune; Jette Viethen; Iris Hendrickx

GRAPH: the costs of redundancy in referring expressions

Emiel Krahmer^*, Mariët Theune, Jette Viethen, Iris Hendrickx

^*Corresponding author for this work

Faculty of Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

10 Citations (Scopus)

Abstract

We describe a graph-based generation system that participated in the TUNA attribute selection and realisation task of the REG 2008 Challenge. Using a stochastic cost function (with certain properties for free), and trying attributes from cheapest to more expensive, the system achieves overall .76 DICE and .54 MASI scores for attribute selection on the development set. For realisation, it turns out that in some cases higher attribute selection accuracy leads to larger differences between system-generated and human descriptions.

Original language	English
Title of host publication	Proceedings of the Fifth International Natural Language Generation Conference
Place of Publication	Stroudsburg, PA
Publisher	Association for Computational Linguistics (ACL)
Pages	227-229
Number of pages	3
Publication status	Published - 2008
Event	5th International Natural Language Generation Conference, INLG 2008 - Salt Fork, OH, United States Duration: 12 Jun 2008 → 14 Jun 2008

Other

Other	5th International Natural Language Generation Conference, INLG 2008
Country/Territory	United States
City	Salt Fork, OH
Period	12/06/08 → 14/06/08

Cite this

@inproceedings{4dfb74f886e44e2aaacfba68b60b8720,

title = "GRAPH: the costs of redundancy in referring expressions",

abstract = "We describe a graph-based generation system that participated in the TUNA attribute selection and realisation task of the REG 2008 Challenge. Using a stochastic cost function (with certain properties for free), and trying attributes from cheapest to more expensive, the system achieves overall .76 DICE and .54 MASI scores for attribute selection on the development set. For realisation, it turns out that in some cases higher attribute selection accuracy leads to larger differences between system-generated and human descriptions.",

author = "Emiel Krahmer and Mari{\"e}t Theune and Jette Viethen and Iris Hendrickx",

year = "2008",

language = "English",

pages = "227--229",

booktitle = "Proceedings of the Fifth International Natural Language Generation Conference",

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

note = "5th International Natural Language Generation Conference, INLG 2008 ; Conference date: 12-06-2008 Through 14-06-2008",

}

Krahmer, E, Theune, M, Viethen, J & Hendrickx, I 2008, GRAPH: the costs of redundancy in referring expressions. in Proceedings of the Fifth International Natural Language Generation Conference. Association for Computational Linguistics (ACL), Stroudsburg, PA, pp. 227-229, 5th International Natural Language Generation Conference, INLG 2008, Salt Fork, OH, United States, 12/06/08.

GRAPH: the costs of redundancy in referring expressions. / Krahmer, Emiel; Theune, Mariët; Viethen, Jette et al.
Proceedings of the Fifth International Natural Language Generation Conference. Stroudsburg, PA: Association for Computational Linguistics (ACL), 2008. p. 227-229.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - GRAPH

T2 - 5th International Natural Language Generation Conference, INLG 2008

AU - Krahmer, Emiel

AU - Theune, Mariët

AU - Viethen, Jette

AU - Hendrickx, Iris

PY - 2008

Y1 - 2008

N2 - We describe a graph-based generation system that participated in the TUNA attribute selection and realisation task of the REG 2008 Challenge. Using a stochastic cost function (with certain properties for free), and trying attributes from cheapest to more expensive, the system achieves overall .76 DICE and .54 MASI scores for attribute selection on the development set. For realisation, it turns out that in some cases higher attribute selection accuracy leads to larger differences between system-generated and human descriptions.

AB - We describe a graph-based generation system that participated in the TUNA attribute selection and realisation task of the REG 2008 Challenge. Using a stochastic cost function (with certain properties for free), and trying attributes from cheapest to more expensive, the system achieves overall .76 DICE and .54 MASI scores for attribute selection on the development set. For realisation, it turns out that in some cases higher attribute selection accuracy leads to larger differences between system-generated and human descriptions.

UR - http://www.scopus.com/inward/record.url?scp=84856146872&partnerID=8YFLogxK

M3 - Conference proceeding contribution

AN - SCOPUS:84856146872

SP - 227

EP - 229

BT - Proceedings of the Fifth International Natural Language Generation Conference

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg, PA

Y2 - 12 June 2008 through 14 June 2008

ER -

GRAPH: the costs of redundancy in referring expressions

Abstract

Other

Other files and links

Fingerprint

Cite this