Please use this identifier to cite or link to this item:
Title: Non-deterministic attribute selection in reference production
Authors: Gatt, Albert
van Gompel, Roger P. G.
Krahmer, Emiel
van Deemter, Kees
Keywords: Natural language processing (Computer science)
Corpora (Linguistics)
Linguistic analysis (Linguistics)
Reference (Linguistics)
Word (Linguistics)
Issue Date: 2011
Publisher: Language, Communication and Cognition
Citation: Gatt, A., van Gompel, R., Krahmer, E., & van Deemter, K. (2011). Non-deterministic attribute selection in reference production. 33rd Annual Meeting of the Cognitive Science Society, Boston. 1-7.
Abstract: In producing identifying descriptions, speakers often overspecify and manifest preferences for certain at-tributes. However, current computational models which incorporate this observation tend not to make precise predictions about when and how much speakers do this. The present paper proposes and evaluates two alter-native models, based on the results of a new experi-ment. Unlike current models, the new ones are non-deterministic and seek to make precise quantitative pre-dictions about the extent to which speakers overspecify.
Appears in Collections:Scholarly Works - InsLin

Files in This Item:
File Description SizeFormat 
precogsci2011.pdf437.7 kBAdobe PDFView/Open

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