Computing word senses by semantic mirroring and spectral graph partitioning

Authors:
Martin Fagerlund;Magnus Merkel;Lars Eldén;Lars Ahrenberg
Affiliations:
Linköping University, Linköping, Sweden;Linköping University, Linköping, Sweden;Linköping University, Linköping, Sweden;Linköping University, Linköping, Sweden
Venue:
TextGraphs-5 Proceedings of the 2010 Workshop on Graph-based Methods for Natural Language Processing
Year:
2010

Citing 2
Cited 0

Distinguishing systems and distinguishing senses: new evaluation methods for Word Sense Disambiguation

Natural Language Engineering
An unsupervised method for word sense tagging using parallel corpora

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Using the technique of "semantic mirroring" a graph is obtained that represents words and their translations from a parallel corpus or a bilingual lexicon. The connectedness of the graph holds information about the different meanings of words that occur in the translations. Spectral graph theory is used to partition the graph, which leads to a grouping of the words according to different senses. We also report results from an evaluation using a small sample of seed words from a lexicon of Swedish and English adjectives.