Are All Good Word Vector Spaces Isomorphic?

Ivan Vulić, Sebastian Ruder, Anders Søgaard
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
Existing algorithms for aligning cross-lingual word vector spaces assume that vector spaces are approximately isomorphic. As a result, they perform poorly or fail completely on nonisomorphic spaces. Such non-isomorphism has been hypothesised to result from typological differences between languages. In this work, we ask whether non-isomorphism is also crucially a sign of degenerate word vector spaces. We present a series of experiments across diverse languages which show that variance in
more » ... nce across language pairs is not only due to typological differences, but can mostly be attributed to the size of the monolingual resources available, and to the properties and duration of monolingual training (e.g. "under-training").
doi:10.18653/v1/2020.emnlp-main.257 fatcat:q6ah6muwnvblbhn6wmhtchifrm