Please use this identifier to cite or link to this item:
Title: Introducing shared task evaluation to NLG : the TUNA shared task evaluation challenges
Other Titles: Empirical methods in natural language generation : data-oriented methods and empirical evaluation
Authors: Gatt, Albert
Belz, Anja
Keywords: Natural language processing (Computer science)
Corpora (Linguistics)
Linguistic analysis (Linguistics)
Reference (Linguistics)
Word (Linguistics)
Issue Date: 2010
Publisher: Springer-Verlag Berlin Heidelberg
Citation: Gatt, A., & Belz, A. (2010). introducing shared tasks to NLG: the TUNA shared task evaluation challenges. In E. Krahmer, & M. Theune (Eds.), Empirical methods in natural language generation: data-oriented methods and empirical evaluation (pp. 264-293). Heidelberg: Springer-Verlag Berlin Heidelberg.
Abstract: Shared Task Evaluation Challenges (stecs) have only recently begun in the field of nlg. The tuna stecs, which focused on Referring Expression Generation (reg), have been part of this development since its inception. This chapter looks back on the experience of organising the three tuna Challenges, which came to an end in 2009. While we discuss the role of the stecs in yielding a substantial body of research on the reg problem, which has opened new avenues for future research, our main focus is on the role of different evaluation methods in assessing the output quality of reg algorithms, and on the relationship between such methods.
ISBN: 9783642155727
Appears in Collections:Scholarly Works - InsLin

Files in This Item:
File Description SizeFormat 
tunareg-bkchapter.pdf491.41 kBAdobe PDFView/Open

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