Good Neighbors Make Good Senses: Exploiting Distributional Similarity for Unsupervised WSD

Samuel Brody, Mirella Lapata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present an automatic method for sense-labeling of text in an unsupervised manner. The method makes use of distributionally similar words to derive an automatically labeled training set, which is then used to train a standard supervised classifier for distinguishing word senses. Experimental results on the Senseval-2 and Senseval-3 datasets show that our approach yields significant improvements over state-of-the-art unsupervised methods, and is competitive with supervised ones, while eliminating the annotation cost.
Original languageEnglish
Title of host publicationProceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)
PublisherAssociation for Computational Linguistics
Pages65-72
Number of pages8
Publication statusPublished - 2008

Fingerprint Dive into the research topics of 'Good Neighbors Make Good Senses: Exploiting Distributional Similarity for Unsupervised WSD'. Together they form a unique fingerprint.

Cite this