GRI: Graph-based Relative Isomorphism of Word Embedding Spaces
This work addresses a core challenge in machine translation for improving bilingual dictionary quality, though it appears incremental as it builds on existing methods with a novel integration.
The paper tackles the problem of constructing bilingual dictionaries from monolingual word embeddings by addressing the geometric similarity (isomorphism) of embedding spaces, and it shows that GRI improves average P@1 by up to 63.6% relative to existing methods.
Automated construction of bilingual dictionaries using monolingual embedding spaces is a core challenge in machine translation. The end performance of these dictionaries relies upon the geometric similarity of individual spaces, i.e., their degree of isomorphism. Existing attempts aimed at controlling the relative isomorphism of different spaces fail to incorporate the impact of semantically related words in the training objective. To address this, we propose GRI that combines the distributional training objectives with attentive graph convolutions to unanimously consider the impact of semantically similar words required to define/compute the relative isomorphism of multiple spaces. Experimental evaluation shows that GRI outperforms the existing research by improving the average P@1 by a relative score of up to 63.6%. We release the codes for GRI at https://github.com/asif6827/GRI.