Unsupervised Word Translation Pairing using Refinement based Point Set Registration

Cross-lingual alignment of word embeddings play an important role in knowledge transfer across languages . This paper proposes BioSpere, a novel framework for unsupervised mapping of bi-lingually word embeddeddings onto a shared vector space, by combining adversarial initialization and refinement procedure with point set registration algorithm used in image processing . We show that our framework alleviates the shortcomings of existing methodologies, and is relatively invariant to variable adversarial learning performance, depicting robustness in terms of parameter choices and training losses . Experimental evaluation on parallel dictionary induction task demonstrates state-of-the-art results for our framework on diverse language pairs. The framework is relatively robust to variable learning performance, and depicts robustness

Links: PDF - Abstract

Code :


Keywords : framework - word - point - adversarial - variable -

Leave a Reply

Your email address will not be published. Required fields are marked *