Gromov-Wasserstein Alignment of Word Embedding Spaces

David Alvarez-Melis, Tommi Jaakkola


Abstract
Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have become effective alignment tools. Current state-of-the-art methods, however, involve multiple steps, including heuristic post-hoc refinement strategies. In this paper, we cast the correspondence problem directly as an optimal transport (OT) problem, building on the idea that word embeddings arise from metric recovery algorithms. Indeed, we exploit the Gromov-Wasserstein distance that measures how similarities between pairs of words relate across languages. We show that our OT objective can be estimated efficiently, requires little or no tuning, and results in performance comparable with the state-of-the-art in various unsupervised word translation tasks.
Anthology ID:
D18-1214
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:
1881–1890
Language:
URL:
https://aclanthology.org/D18-1214
DOI:
10.18653/v1/D18-1214
Bibkey:
Cite (ACL):
David Alvarez-Melis and Tommi Jaakkola. 2018. Gromov-Wasserstein Alignment of Word Embedding Spaces. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1881–1890, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Gromov-Wasserstein Alignment of Word Embedding Spaces (Alvarez-Melis & Jaakkola, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1214.pdf
Video:
 https://aclanthology.org/D18-1214.mp4