Towards Large-scale High-Performance English Verb Sense Disambiguation by Using Linguistically Motivated Features

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Jinying Chen Articles by Dmitriy Dligach Articles by Martha Palmer

International Conference on Semantic Computing (ICSC 2007)

Irvine, California

September 17-September 19

ISBN: 0-7695-2997-6

	ASCII Text	x
	Jinying Chen, Dmitriy Dligach, Martha Palmer, "Towards Large-scale High-Performance English Verb Sense Disambiguation by Using Linguistically Motivated Features," International Conference on Semantic Computing, pp. 378-388, International Conference on Semantic Computing (ICSC 2007), 2007.

	BibTex	x
	@article{ 10.1109/ICSC.2007.69, author = {Jinying Chen and Dmitriy Dligach and Martha Palmer}, title = {Towards Large-scale High-Performance English Verb Sense Disambiguation by Using Linguistically Motivated Features}, journal ={International Conference on Semantic Computing}, volume = {0}, year = {2007}, isbn = {0-7695-2997-6}, pages = {378-388}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICSC.2007.69}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - International Conference on Semantic Computing TI - Towards Large-scale High-Performance English Verb Sense Disambiguation by Using Linguistically Motivated Features SN - 0-7695-2997-6 SP378 EP388 A1 - Jinying Chen, A1 - Dmitriy Dligach, A1 - Martha Palmer, PY - 2007 KW - null VL - 0 JA - International Conference on Semantic Computing ER -

Jinying Chen, BBN Technologies

Dmitriy Dligach, University of Colorado at Boulder, USA

Martha Palmer, University of Colorado at Boulder, USA

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICSC.2007.69

In this paper we describe the results of training high performance Word Sense Disambiguation (WSD) systems on a new data set based on groupings of WordNet senses. This data set is designed to provide clear sense distinctions with sufficient examples in order to provide high quality training data. The sense distinctions are based on explicit syntactic and semantic criteria. Our WSD features utilize similar syntactic and semantic linguistic information. We demonstrate that this approach, using both Maximum Entropy and SVM models, produces systems whose performance is comparable to that of humans.

Citation:

Jinying Chen, Dmitriy Dligach, Martha Palmer, "Towards Large-scale High-Performance English Verb Sense Disambiguation by Using Linguistically Motivated Features," icsc, pp.378-388, International Conference on Semantic Computing (ICSC 2007), 2007

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.