Paper: Using Syntactic Dependency As Local Context To Resolve Word Sense Ambiguity

ACL ID P97-1009
Title Using Syntactic Dependency As Local Context To Resolve Word Sense Ambiguity
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1997
Authors
  • Dekang Lin (University of Manitoba, Winnipeg MB)

Most previous corpus-based algorithms dis- ambiguate 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 algo- rithm does not require a sense-tagged cor- pus and exploits the fact that two different words are likely to have similar meanings if they occur in identical local contexts.