A Multi-Pairwise Extension of Procrustes Analysis for Multilingual Word Translation

Hagai Taitelbaum, Gal Chechik, Jacob Goldberger

Abstract
In this paper we present a novel approach to simultaneously representing multiple languages in a common space. Procrustes Analysis (PA) is commonly used to find the optimal orthogonal word mapping in the bilingual case. The proposed Multi Pairwise Procrustes Analysis (MPPA) is a natural extension of the PA algorithm to multilingual word mapping. Unlike previous PA extensions that require a k-way dictionary, this approach requires only pairwise bilingual dictionaries that are much easier to construct.
Anthology ID:
D19-1363
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3560–3565
Language:
URL:
https://aclanthology.org/D19-1363
DOI:
10.18653/v1/D19-1363
Bibkey:
Cite (ACL):
Hagai Taitelbaum, Gal Chechik, and Jacob Goldberger. 2019. A Multi-Pairwise Extension of Procrustes Analysis for Multilingual Word Translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3560–3565, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
A Multi-Pairwise Extension of Procrustes Analysis for Multilingual Word Translation (Taitelbaum et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/D19-1363.pdf
PDF Search