Memory-based learning for article generation

Article choice can pose difficult problems in applications such as machine translation and automated summarization. In this paper, we investigate the use of corpus data to collect statistical generalizations about article use in English in order to be able to generate articles automatically to suppl...

Full description

Saved in:

Bibliographic Details
Main Authors:	Minnen, Guido, Bond, Francis, Copestake, Ann
Other Authors:	School of Humanities and Social Sciences
Format:	Conference or Workshop Item
Language:	English
Published:	2011
Subjects:	DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
Online Access:	https://hdl.handle.net/10356/83964 http://hdl.handle.net/10220/7246
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-83964
record_format	dspace
spelling	sg-ntu-dr.10356-839642020-03-07T12:10:36Z Memory-based learning for article generation Minnen, Guido Bond, Francis Copestake, Ann School of Humanities and Social Sciences Conference on Computational Language Learning (4th : 2000 : Lisbon, Portugal) DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics Article choice can pose difficult problems in applications such as machine translation and automated summarization. In this paper, we investigate the use of corpus data to collect statistical generalizations about article use in English in order to be able to generate articles automatically to supplement a symbolic generator. We use data from the Penn Treebank as input to a memory-based learner (TiMBL 3.0; Daelemans et al., 2000) which predicts whether to generate an article with respect to an English base noun phrase. We discuss competitive results obtained using a variety of lexical, syntactic and semantic features that play an important role in automated article generation. Published version 2011-10-12T06:53:13Z 2019-12-06T15:35:26Z 2011-10-12T06:53:13Z 2019-12-06T15:35:26Z 2000 2000 Conference Paper Minnen, G., Bond, F. & Copestake, A. (2000). Memory-based learning for article generation. Proceedings of Conference on Computational Language Learning, Lisbon, pp.43–48. https://hdl.handle.net/10356/83964 http://hdl.handle.net/10220/7246 10.3115/1117601.1117611 155597 en © 2000 Association for Computational Linguistics. This paper was published in Proceedings of Conference on Computational Language Learning and is made available as an electronic reprint (preprint) with permission of Association for Computational Linguistics. The paper can be found at the following official URL: http://dx.doi.org/10.3115/1117601.1117611. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law. 6 p. application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
spellingShingle	DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics Minnen, Guido Bond, Francis Copestake, Ann Memory-based learning for article generation
description	Article choice can pose difficult problems in applications such as machine translation and automated summarization. In this paper, we investigate the use of corpus data to collect statistical generalizations about article use in English in order to be able to generate articles automatically to supplement a symbolic generator. We use data from the Penn Treebank as input to a memory-based learner (TiMBL 3.0; Daelemans et al., 2000) which predicts whether to generate an article with respect to an English base noun phrase. We discuss competitive results obtained using a variety of lexical, syntactic and semantic features that play an important role in automated article generation.
author2	School of Humanities and Social Sciences
author_facet	School of Humanities and Social Sciences Minnen, Guido Bond, Francis Copestake, Ann
format	Conference or Workshop Item
author	Minnen, Guido Bond, Francis Copestake, Ann
author_sort	Minnen, Guido
title	Memory-based learning for article generation
title_short	Memory-based learning for article generation
title_full	Memory-based learning for article generation
title_fullStr	Memory-based learning for article generation
title_full_unstemmed	Memory-based learning for article generation
title_sort	memory-based learning for article generation
publishDate	2011
url	https://hdl.handle.net/10356/83964 http://hdl.handle.net/10220/7246
_version_	1681047556690280448

Memory-based learning for article generation

Similar Items