MSDA: Wordsense Discrimination Using Context Vectors and Attributes

Authors:
Abdulrahman Almuhareb;Massimo Poesio
Affiliations:
University of Essex, UK, email: aalmuh & poesio at essex.ac.uk;University of Essex, UK, email: aalmuh & poesio at essex.ac.uk and University of Trento, Italy
Venue:
Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Year:
2006

Citing 11
Cited 1

Concepts, attributes and arbitrary relations: some linguistic and ontological criteria for structuring knowledge bases

Data & Knowledge Engineering - Special issue on linguistic instruments in knowledge engineering (LIKE)
Dimensions of meaning

Proceedings of the 1992 ACM/IEEE conference on Supercomputing
Explorations in Automatic Thesaurus Discovery

Explorations in Automatic Thesaurus Discovery
Discovering word senses from text

Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
The description logic handbook: theory, implementation, and applications

The description logic handbook: theory, implementation, and applications
Automatic word sense discrimination

Computational Linguistics - Special issue on word sense disambiguation
Automatic retrieval and clustering of similar words

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Automatic construction of a hypernym-labeled noun hierarchy from text

ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Discovering corpus-specific word senses

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 2
Improvements in automatic thesaurus extraction

ULA '02 Proceedings of the ACL-02 workshop on Unsupervised lexical acquisition - Volume 9
Identifying concept attributes using a classifier

DeepLA '05 Proceedings of the ACL-SIGLEX Workshop on Deep Lexical Acquisition

A methodology to learn ontological attributes from the Web

Data & Knowledge Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present MSDA (Major Senses Discovery Algorithm) --a development over the context vector approach to (noun) sense discrimination [20, 24] that uses attributes and values instead of word features to cluster contexts, and does not require for the number of senses to be fixed beforehand. The algorithm achieves a precision of 89% on a dataset including both ambiguous and non-ambiguous nouns, twice that of previous algorithms.