1 code implementation • WS 2017 • Avo Muromägi, Kairit Sirts, Sven Laur
The results show that while using the ordinary least squares regression performs poorly in our experiments, using orthogonal Procrustes to combine several word embedding models into an ensemble model leads to 7-10% relative improvements over the mean result of the initial models in synonym tests and 19-47% in analogy tests.