mirage

A plethora of methods for learning English countability

DSpace/Manakin Repository

 

Search DR-NTU


Advanced Search Subject Search

Browse

My Account

A plethora of methods for learning English countability

Show full item record

Title: A plethora of methods for learning English countability
Author: Baldwin, Timothy; Bond, Francis
Copyright year: 2003
Abstract: This paper compares a range of methods for classifying words based on linguistic diagnostics, focusing on the task of learning countabilities for English nouns. We propose two basic approaches to feature representation: distribution-based representation, which simply looks at the distribution of features in the corpus data, and agreement-based representation which analyses the level of tokenwise agreement between multiple preprocessor systems. We additionally compare a single multiclass classifier architecture with a suite of binary classifiers, and combine analyses from multiple preprocessors. Finally, we present and evaluate a feature selection method.
Subject: DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
Type: Conference Paper
Conference name: Conference on Empirical Methods in Natural Language Processing (2003)
School: School of Humanities and Social Sciences
Rights: © 2003 ACL. This is the author created version of a work that has been peer reviewed and accepted for publication by Proceedings of 2003 Conference on Empirical Methods in Natural Language Processing: EMNLP 2003, Association for Computational Linguistics. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [DOI: http://dx.doi.org/10.3115/1119355.1119365].
Version: Accepted version

Files in this item

Files Size Format View
2003-emnlp-count-ml.pdf 142.1Kb 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
A plethora of methods for learning English countability 384

Total downloads

All Bitstreams Views
2003-emnlp-count-ml.pdf 208

Top country downloads

Country Code Views
China 75
United States of America 70
Singapore 25
United Kingdom 6
France 5

Top city downloads

city Views
Beijing 59
Mountain View 52
Singapore 25
Southampton 4
Bangkok 2

Downloads / month

  2014-09 2014-10 2014-11 total
2003-emnlp-count-ml.pdf 0 0 7 7