Learning the Countability of English Nouns from Corpus Data (2003)
Cached
Download Links
- [acl.ldc.upenn.edu]
- [acl.ldc.upenn.edu]
- [acl.ldc.upenn.edu]
- [lingo.stanford.edu]
- [acl.ldc.upenn.edu]
- [www-csli.stanford.edu]
- [www.cs.mu.oz.au]
- DBLP
Other Repositories/Bibliography
by
Timothy Baldwin
,
Francis Bond
| Venue: | IN PROC. OF THE 41ST ANNUAL MEETING OF THE ACL |
| Citations: | 12 - 5 self |
BibTeX
@INPROCEEDINGS{Baldwin03learningthe,
author = {Timothy Baldwin and Francis Bond},
title = {Learning the Countability of English Nouns from Corpus Data},
booktitle = {IN PROC. OF THE 41ST ANNUAL MEETING OF THE ACL},
year = {2003},
pages = {463--470},
publisher = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper describes a method for learning the countability preferences of English nouns from raw text corpora. The method maps the corpus-attested lexico-syntactic properties of each noun onto a feature vector, and uses a suite of memory-based classifiers to predict membership in 4 countability classes. We were able to assign countability to English nouns with a precision of 94.6%.
