Word sense disambiguation algorithms, with few ex- ceptions, have made use of only one lexical know- ledge source. We describe a system which t)erforms word sense disambiguation on all content words in free text by combining different knowledge sources: semantic preferences, dictionary definitions and sub- ject/domain codes along with part-of-speech tags, optimised by means of a learning algorithm. We also describe the creation of a new sense tagged corpus by combining existing resources. Tested accuracy of our approach on this corpus exceeds 92%, demonstrat- ing the viability of all-word disambiguation rather than restricting oneself to a small sample.

Click Here to View the Paper In XML Format