We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the much simplified bilingual setting, by picking one of the input languages as the pivot language that we transit through. However, it is well-known that transiting through a poorly chosen pivot language (such as English) may severely degrade the translation quality, since the assumed transitive relations among all pairs of languages may not be enforced in the training process. Instead of going through a rather arbitrarily chosen pivot language, we propose to use the Wasserstein barycenter as a more informative ”mean” language: it encapsulates information from all languages and minimizes all pairwise transportation costs. We evaluate our method on standard benchmarks and demonstrate state-of-the-art performances.
Bibtex
@misc{lian2020unsupervised,
title={Unsupervised Multilingual Alignment using Wasserstein Barycenter},
author={Xin Lian and Kshitij Jain and Jakub Truszkowski and Pascal Poupart and Yaoliang Yu},
year={2020},
eprint={2002.00743},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Related Research
-
Adversarial Robustness with AdverTorch Black-box Estimators
Adversarial Robustness with AdverTorch Black-box Estimators
M. Safa, and G. Castiglione.
Computer Vision; Natural Language Processing; Responsible AI
Research
-
Inside our Top 5 Responsible AI Papers from ACL 2022
Inside our Top 5 Responsible AI Papers from ACL 2022
D. Silverberg.
Research
-
Our NeurIPS 2021 Reading List
Our NeurIPS 2021 Reading List
Y. Cao, K. Y. C. Lui, T. Durand, J. He, P. Xu, N. Mehrasa, A. Radovic, A. Lehrmann, R. Deng, A. Abdi, M. Schlegel, and S. Liu.
Computer Vision; Data Visualization; Graph Representation Learning; Learning And Generalization; Natural Language Processing; Optimization; Reinforcement Learning; Time series Modelling; Unsupervised Learning
Research