Are All Good Word Vector Spaces Isomorphic?
Published version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Vulic, Ivan
Ruder, Sebastian
Søgaard, Anders
Abstract
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 non-isomorphic 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 performance 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").
Description
Keywords
Journal Title
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
Conference Name
Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
Journal ISSN
Volume Title
Publisher
Association for Computational Linguistics
Publisher DOI
Rights
All rights reserved
Sponsorship
European Research Council (648909)