0
Gromov-Wasserstein Alignment of Word Embedding Spaces
David Alvarez-Melis, Tommi Jaakkola, 2018. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.
Treats unsupervised alignment of word embeddings in two languages as an optimal transport problem, using the Gromov-Wasserstein distance to compare how words relate to one another within each space.
What it's used for here
The emerging-methods survey cites it for the Gromov-Wasserstein algorithm in its sections on cross-lingual embedding alignment and network alignment.
Cited by on this site 1 record
1 methods surveys
SRCMathematics
Cite it
Alvarez-Melis, D., & Jaakkola, T. (2018). Gromov-Wasserstein Alignment of Word Embedding Spaces. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/d18-1214
@article{alvarezmelis2018gromov,
author = {Alvarez-Melis, David and Jaakkola, Tommi},
title = {Gromov-Wasserstein Alignment of Word Embedding Spaces},
journal = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
year = {2018},
doi = {10.18653/v1/d18-1214},
url = {https://doi.org/10.18653/v1/d18-1214}
}TY - JOUR TI - Gromov-Wasserstein Alignment of Word Embedding Spaces AU - Alvarez-Melis, David AU - Jaakkola, Tommi PY - 2018 JO - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing DO - 10.18653/v1/d18-1214 UR - https://doi.org/10.18653/v1/d18-1214 ER -
Alvarez-Melis, David and Tommi Jaakkola. “Gromov-Wasserstein Alignment of Word Embedding Spaces.” Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018). https://doi.org/10.18653/v1/d18-1214.