mirage

Memory-based learning for article generation.

DSpace/Manakin Repository

 

Search DR-NTU


Advanced Search Subject Search

Browse

My Account

Memory-based learning for article generation.

Show full item record

Title: Memory-based learning for article generation.
Author: Minnen, Guido.; Bond, Francis.; Copestake, Ann.
Copyright year: 2000
Abstract: 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.
Subject: DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics.
Type: Conference Paper
Conference name: Conference on Computational Language Learning (4th : 2000 : Lisbon, Portugal)
School: College of Humanities, Arts, and Social Sciences
Rights: © 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.
Version: Published version

Files in this item

Files Size Format View
10.1.1.33.2086.pdf 104.1Kb PDF View/Open
   

DOI Query

- Get published version (via Digital Object Identifier)
   

This item appears in the following Collection(s)

Show full item record

Statistics

Total views

All Items Views
Memory-based learning for article generation. 385

Total downloads

All Bitstreams Views
10.1.1.33.2086.pdf 397

Top country downloads

Country Code Views
China 95
United States of America 86
Thailand 27
Singapore 23
France 13

Top city downloads

city Views
Beijing 57
Mountain View 39
Singapore 23
Bangkok 19
Chicago 9

Downloads / month

  2014-10 2014-11 2014-12 total
10.1.1.33.2086.pdf 0 0 12 12