Clusty is an innovative algorithm designed to perform lexical-semantic analytics for NLP: sense clustering. The team at the Linguistic Computing Laboratory of the Sapienza University of Rome investigated clustering approaches which allow to effectively and easily scale across languages whilst dropping the requirement of large amounts of data which is typically needed when employing neural networks. Clusty’s results can be used for improving word sense disambiguation systems. The demonstration of the efficacy of Clusty for performing one of the most challenging tasks in natural language processing, sense clustering, is presented in D3.1 (below). For installation we provide the link to GitHub repository.
