Unsupervised Multilingual Word Embeddings

Xilun Chen, Claire Cardie


Abstract
Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant advantage over traditional supervised approaches and opens many new possibilities for low-resource languages. Prior art for learning UMWEs, however, merely relies on a number of independently trained Unsupervised Bilingual Word Embeddings (UBWEs) to obtain multilingual embeddings. These methods fail to leverage the interdependencies that exist among many languages. To address this shortcoming, we propose a fully unsupervised framework for learning MWEs that directly exploits the relations between all language pairs. Our model substantially outperforms previous approaches in the experiments on multilingual word translation and cross-lingual word similarity. In addition, our model even beats supervised approaches trained with cross-lingual resources.
Anthology ID:
D18-1024
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
261–270
Language:
URL:
https://aclanthology.org/D18-1024
DOI:
10.18653/v1/D18-1024
Bibkey:
Cite (ACL):
Xilun Chen and Claire Cardie. 2018. Unsupervised Multilingual Word Embeddings. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 261–270, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Multilingual Word Embeddings (Chen & Cardie, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1024.pdf
Code
 ccsasuke/umwe +  additional community code