Unsupervised Alignment of Distributional Word Embeddings. (arXiv:2203.04863v2 [cs.CL] UPDATED)

Cross-domain alignment play a key roles in tasks ranging from machine
translation to transfer learning. Recently, purely unsupervised methods
operating on monolingual embeddings have successfully been used to infer a
bilingual lexicon without relying on supervision. However, current state-of-the
art methods only focus on point vectors although distributional embeddings have
proven to embed richer semantic information when representing words. In this
paper, we propose stochastic optimization approach for aligning probabilistic
embeddings. Finally, we evaluate our method on the problem of …

alignment arxiv unsupervised word embeddings