Beyond DICE: measuring the quality of a referring expression

Kees van Deemter; Albert Gatt

Beyond DICE: measuring the quality of a referring expression

Kees van Deemter, Albert Gatt

Computing Science

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

Abstract

This paper discusses ways in which the similarity between the contents of two referring expressions can be measured. Similarity metrics of this kind are essential when expressions generated by an algoritm are compared against the ones produced by human speakers, for example as part of an experiment in which referring expressions are elicitated. We discuss arguments for and against different metrics, taking our departure from the well-known Dice metric.

Original language	English
Title of host publication	Proceedings of "Production of Referring Expressions''
Publisher	Cognitive Science Society
Number of pages	3
Publication status	Published - Jul 2009
Event	PRE-CogSci 2009 - Amsterdam, Netherlands Duration: 29 Jul 2009 → …

Conference

Conference	PRE-CogSci 2009
Country/Territory	Netherlands
City	Amsterdam
Period	29/07/09 → …

Keywords

DICE
generation of referring expressions
evaluation metrics

Access to Document

http://homepages.abdn.ac.uk/k.vdeemter/pages/vandeemter_gatt-dice_PRE.pdf

Cite this

@inproceedings{d6cf672943324e53a67a1c3286067535,

title = "Beyond DICE: measuring the quality of a referring expression",

abstract = "This paper discusses ways in which the similarity between the contents of two referring expressions can be measured. Similarity metrics of this kind are essential when expressions generated by an algoritm are compared against the ones produced by human speakers, for example as part of an experiment in which referring expressions are elicitated. We discuss arguments for and against different metrics, taking our departure from the well-known Dice metric.",

keywords = "DICE, generation of referring expressions, evaluation metrics",

author = "{van Deemter}, Kees and Albert Gatt",

year = "2009",

month = jul,

language = "English",

booktitle = "Proceedings of {"}Production of Referring Expressions''",

publisher = "Cognitive Science Society",

note = "PRE-CogSci 2009 ; Conference date: 29-07-2009",

}

TY - GEN

T1 - Beyond DICE

T2 - PRE-CogSci 2009

AU - van Deemter, Kees

AU - Gatt, Albert

PY - 2009/7

Y1 - 2009/7

N2 - This paper discusses ways in which the similarity between the contents of two referring expressions can be measured. Similarity metrics of this kind are essential when expressions generated by an algoritm are compared against the ones produced by human speakers, for example as part of an experiment in which referring expressions are elicitated. We discuss arguments for and against different metrics, taking our departure from the well-known Dice metric.

AB - This paper discusses ways in which the similarity between the contents of two referring expressions can be measured. Similarity metrics of this kind are essential when expressions generated by an algoritm are compared against the ones produced by human speakers, for example as part of an experiment in which referring expressions are elicitated. We discuss arguments for and against different metrics, taking our departure from the well-known Dice metric.

KW - DICE

KW - generation of referring expressions

KW - evaluation metrics

M3 - Published conference contribution

BT - Proceedings of "Production of Referring Expressions''

PB - Cognitive Science Society

Y2 - 29 July 2009

ER -

Beyond DICE: measuring the quality of a referring expression

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this