Please use this identifier to cite or link to this item:
Title: Beyond DICE : measuring the quality of a referring expression
Authors: van Deemter, Kees
Gatt, Albert
Keywords: Natural language processing (Computer science)
Corpora (Linguistics)
Linguistic analysis (Linguistics)
Reference (Linguistics)
Word (Linguistics)
Issue Date: 2009
Publisher: Cognitive Science Society
Citation: Van Deemter, K., & Gatt, A. (2009). Beyond DICE: measuring the quality of a referring expression. 31st Annual Meeting of the Cognitive Science Society, Amsterdam. 1-3.
Abstract: This paper discusses ways in which the similarity between the contents of two referring expressions can be measured. Simi- larity metrics of this kind are essential when expressions gen- erated 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 argu- ments for and against different metrics, taking our departure from the well-known Dice metric.
ISBN: 9781615674077
Appears in Collections:Scholarly Works - InsLin

Files in This Item:
File Description SizeFormat 
pre-Dice.pdf84.51 kBAdobe PDFView/Open

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.