Evaluating a Joint Training Approach for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora on Lower-resource Languages

Ali Hakimi Parizi, Paul Cook


Abstract
Cross-lingual word embeddings provide a way for information to be transferred between languages. In this paper we evaluate an extension of a joint training approach to learning cross-lingual embeddings that incorporates sub-word information during training. This method could be particularly well-suited to lower-resource and morphologically-rich languages because it can be trained on modest size monolingual corpora, and is able to represent out-of-vocabulary words (OOVs). We consider bilingual lexicon induction, including an evaluation focused on OOVs. We find that this method achieves improvements over previous approaches, particularly for OOVs.
Anthology ID:
2021.starsem-1.29
Volume:
Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
Month:
August
Year:
2021
Address:
Online
Venues:
*SEM | ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
302–307
Language:
URL:
https://aclanthology.org/2021.starsem-1.29
DOI:
10.18653/v1/2021.starsem-1.29
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.starsem-1.29.pdf
Optional supplementary material:
 2021.starsem-1.29.OptionalSupplementaryMaterial.pdf