Abstract
This paper describes a heuristic approach to word sense disambiguation (WSD) based on automatically acquired word sense division. The semantically related sense entries in a bilingual dictionary are arranged in clusters using a heuristic l ling algorithm to provide a more complete and appropriate sense division for WSD. Translations of entries allocated the same l l serve as outside information sources to tag a bilingual corpus with sense l l for the automatic acquistion of WSD rules. We describe and implement a method of l ling senses in the English-Chinese bilingual version (LecDOCE) of the Longman Dictionary of Contemporary English (LDOCE). For this purpose, we draw on a selection of topics and sets of related words from the Longman Lexicon of Contemporary English (LLOCE). Example sentences and their translations from LecDOCE are employed as training materials for WSD, while further examples from the Brown corpus are used for testing. Quantitative results for a 12-word test set are reported.