Peng, X. orcid.org/0000-0001-5787-9982, Stevenson, R. orcid.org/0000-0002-9483-6006, Lin, C. et al. (1 more author) (2022) Understanding linearity of cross-lingual word embedding mappings. Transactions on Machine Learning Research.
Abstract
The technique of Cross-Lingual Word Embedding (CLWE) plays a fundamental role in tackling Natural Language Processing challenges for low-resource languages. Its dominant approaches assumed that the relationship between embeddings could be represented by a linear mapping, but there has been no exploration of the conditions under which this assumption holds. Such a research gap becomes very critical recently, as it has been evidenced that relaxing mappings to be non-linear can lead to better performance in some cases. We, for the first time, present a theoretical analysis that identifies the preservation of analogies encoded in monolingual word embeddings as a *necessary and sufficient* condition for the ground-truth CLWE mapping between those embeddings to be linear. On a novel cross-lingual analogy dataset that covers five representative analogy categories for twelve distinct languages, we carry out experiments which provide direct empirical support for our theoretical claim. These results offer additional insight into the observations of other researchers and contribute inspiration for the development of more effective cross-lingual representation learning strategies.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022. Article available under a Creative Commons Attribution 4.0 International (http://creativecommons.org/licenses/by/4.0) |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 30 Jun 2022 14:44 |
Last Modified: | 06 Jul 2022 10:40 |
Published Version: | https://openreview.net/forum?id=8HuyXvbvqX |
Status: | Published online |
Publisher: | JMLR Inc |
Refereed: | Yes |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:188519 |