Robust utilization of context in word sense disambiguation

Authors:
Xiaojie Wang
Affiliations:
School of Information Engineering, Beijing University of Posts and Telecommunications, Beijing, China
Venue:
CONTEXT'05 Proceedings of the 5th international conference on Modeling and Using Context
Year:
2005

Citing 10
Cited 5

Foundations of statistical natural language processing

Foundations of statistical natural language processing
Introduction to the special issue on word sense disambiguation: the state of the art

Computational Linguistics - Special issue on word sense disambiguation
Using corpus statistics and WordNet relations for sense identification

Computational Linguistics - Special issue on word sense disambiguation
Evaluating sense disambiguation across diverse parameter spaces

Natural Language Engineering
Word sense disambiguation with pattern learning and automatic feature selection

Natural Language Engineering
A simple approach to building ensembles of Naive Bayesian classifiers for word sense disambiguation

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Decision lists for lexical ambiguity resolution: application to accent restoration in Spanish and French

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Integrating multiple knowledge sources to disambiguate word sense: an exemplar-based approach

ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Combining heterogeneous classifiers for word-sense disambiguation

WSD '02 Proceedings of the ACL-02 workshop on Word sense disambiguation: recent successes and future directions - Volume 8
Modeling consensus: classifier combination for word sense disambiguation

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10

Co-dispersion: a windowless approach to lexical association

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
A comparison of windowless and window-based computational association measures as predictors of syntagmatic human associations

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Local context selection for aligning sentences in parallel corpora

CONTEXT'07 Proceedings of the 6th international and interdisciplinary conference on Modeling and using context
Tracing conceptual and geospatial diffusion of knowledge

OCSC'07 Proceedings of the 2nd international conference on Online communities and social computing
Context-based sentence alignment in parallel corpora

CICLing'08 Proceedings of the 9th international conference on Computational linguistics and intelligent text processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Context is the only means to identify the sense of a polysemous word. All algorithms for word sense disambiguation make use of information within a context window of the target word. What is the best window size for word sense disambiguation has been long a problem. Different contexts generally give different results even for a same algorithm. In this paper, we exploit an algorithm which is more robust with the varying of different context used. This method aims to lower the uncertainty brought by classifiers using different context window sizes and make more robust utilization of context while perform well. Experiments show our approach outperforms some other algorithms on both robustness and performance.