Unsupervised Bilingual Word Sense Disambiguation Using Web Statistics.

Word sense disambiguation has sense division and sense selection as its two sub-problems. An appropriate solution to the sense division problem is usually dependent on the application being pursued. In the context of machine translation, picking the correct translation for a word among multiple candidates, is known as target word selection. The work in this paper uses the Web as the main knowledge source to address the difficulty of making a target word selection based on statistics, which are normally drawn from rather limited corpora. The proposed approach uses simple and easily accessible web statistics-search engine hits (number of document returned for a particular query) to demonstrate the great potential of the Web as a knowledge source for word sense disambiguation. Our experimental results so far are very encouraging. [ABSTRACT FROM AUTHOR]