BibSonomy :: bibtex  ::

tag user group author concept BibTeX key search:all search:stefano
A blue social bookmark and publication sharing system.
tags · relations · groups · popular
help · blog · about
login · register
stefano's BibTeX entry:  

Disambiguating Noun Compounds

Proceedings of the 20th Conference on Artificial Intelligence, 2007.
Authors: Su Nam Kim and Timothy Baldwin
URL: http://www.cs.mu.oz.au/~snkim/documents/aaai07.pdf
Tags: compounds disambiguating nlp noun
Abstract: This paper is concerned with the interaction between word sense disambiguation and the interpretation of noun compounds (NCs) in English. We develop techniques for disambiguating word sense specifically in NCs, and then investigate whether word sense information can aid in the semantic relation interpretation of NCs. To disambiguate word sense, we combine the one sense per collocation heuristic with the grammatical role of polysemous nouns and analysis of word sense combinatorics. We built supervised and unsupervised classifiers for the task and demonstrate that the supervised methods are superior to a number of baselines and also a benchmark state-of-the-art WSD system. Finally, we show that WSD can significantly improve the accuracy of NC interpretation.
| URL | BibTeX  
@inproceedings{Kim:Baldwin:07a,
title = {Disambiguating Noun Compounds},
author = {Su Nam Kim and Timothy Baldwin},
booktitle = {Proceedings of the 20th Conference on Artificial Intelligence},
url = {http://www.cs.mu.oz.au/~snkim/documents/aaai07.pdf},
year = {2007},
abstract = {This paper is concerned with the interaction between word sense disambiguation and the interpretation of noun compounds (NCs) in English. We develop techniques for disambiguating word sense specifically in NCs, and then investigate whether word sense information can aid in the semantic relation interpretation of NCs. To disambiguate word sense, we combine the one sense per collocation heuristic with the grammatical role of polysemous nouns and analysis of word sense combinatorics. We built supervised and unsupervised classifiers for the task and demonstrate that the supervised methods are superior to a number of baselines and also a benchmark state-of-the-art WSD system. Finally, we show that WSD can significantly improve the accuracy of NC interpretation.},
keywords = {compounds disambiguating nlp noun }
}