Extending WordNet using Generalized Automated Relationship Induction

This paper describes a Java package for automatically extending WordNet and other semantic lexicons. Extending these semantic lexicons by traditional means of hand labeling word relationships is a very expensive and laborious process. We used machine learning techniques to automatically extract relationships between words from a given text corpus. The package is made to be very flexible, allowing for various modules, such as new classifiers and semanitic lexions, to be “plugged-in.” The power of the package comes form its ability to seamlessly integrate the Stanford Parser to WordNet. Results obtained for various tests, particularly those done for a Naïve Bayes classifier, are promising.