Please use this identifier to cite or link to this item:
Title: Incremental generation of plural descriptions : similarity and partitioning
Authors: Gatt, Albert
van Deemter, Kees
Keywords: Reference (Linguistics)
Natural language processing (Computer science)
Corpora (Linguistics)
Linguistic analysis (Linguistics)
Issue Date: 2007
Publisher: Association for Computational Linguistics
Citation: Gatt, A., & van Deemter, K. (2007). Incremental generation of plural descriptions: similarity and partitioning. Conference on Empirical Methods in Natural Language Processing Conference on Computational Natural Language Learning, Prague. 102-111.
Abstract: Approaches to plural reference generation emphasise descriptive brevity, but often lack empirical backing. This paper describes a corpus-based study of plural descriptions, and proposes a psycholinguisticallymotivated algorithm for plural reference generation. The descriptive strategy is based on partitioning and incorporates corpusderived heuristics. An exhaustive evaluation shows that the output closely matches human data.
Appears in Collections:Scholarly Works - InsLin

Files in This Item:
File Description SizeFormat 
emnlp2007.pdf187.17 kBAdobe PDFView/Open

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