Using Syntactic Dependency as Local Context to Resolve Word Sense Ambiguity

Most previous corpus-based algorithms disambiguate a word with a classifier trained from previous usages of the same word. Separate classifiers have to be trained for different words. We present an algorithm that uses the same knowledge sources to disambiguate different words. The algorithm does not require a sense-tagged corpus and exploits the fact that two different words are likely to have similar meanings if they occur in identical local contexts.

• Type: Conference
• Year: 1997
• Where: ACL
• Authors: Dekang Lin
• Keywords: ACL 1997, ACL 2007, Identical Local Contexts, Knowledge Sources, Separate Classifiers