“…Obtaining accurate semantic representations of individual word senses or concepts is vital for several applications in Natural Language Processing (NLP) such as, for example, Word Sense Disambiguation (Navigli, 2009;Navigli, 2012), Entity Linking (Bunescu and Paşca, 2006;Rao et al, 2013), semantic similarity (Budanitsky and Hirst, 2006), Information Extraction (Banko et al, 2007), and resource linking and integration (Pilehvar and Navigli, 2014). One prominent semantic representation approach is the distributional semantic model, which represents lexical items as vectors in a semantic space.…”