Align, Disambiguate, and Walk (ADW) is a WordNet-based approach for measuring semantic similarity of arbitrary pairs of lexical items, from word senses to full texts. The approach leverages random walks on semantic networks for modeling lexical items. For more details on ADW please read the following paper:

Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity.

Mohammad Taher Pilehvar, David Jurgens and Roberto Navigli.

The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013) - best paper nominee.

An open-source Java implementation of the similarity measure is available at ADW's github repository.

You can also directly download the jar package and resources with instructions (~ 25MB).

Download the signatures (~ 250MB).