In this paper, we describe our method for detection of lexical semantic\nchange (i.e., word sense changes over time) for the DIACR-Ita shared task,\nwhere we ranked $1^{st}$. We examine semantic differences between specific\nwords in two Italian corpora, chosen from different time periods. Our method is\nfully unsupervised and language independent. It consists of preparing a\nsemantic vector space for each corpus, earlier and later. Then we compute a\nlinear transformation between earlier and later spaces, using CCA and\nOrthogonal Transformation. Finally, we measure the cosines between the\ntransformed vectors.\n