A Locally Linear Procedure for Word Translation

Soham Dan, Hagai Taitelbaum, Jacob Goldberger


Abstract
Learning a mapping between word embeddings of two languages given a dictionary is an important problem with several applications. A common mapping approach is using an orthogonal matrix. The Orthogonal Procrustes Analysis (PA) algorithm can be applied to find the optimal orthogonal matrix. This solution restricts the expressiveness of the translation model which may result in sub-optimal translations. We propose a natural extension of the PA algorithm that uses multiple orthogonal translation matrices to model the mapping and derive an algorithm to learn these multiple matrices. We achieve better performance in a bilingual word translation task and a cross-lingual word similarity task compared to the single matrix baseline. We also show how multiple matrices can model multiple senses of a word.
Anthology ID:
2020.coling-main.528
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6013–6018
Language:
URL:
https://aclanthology.org/2020.coling-main.528
DOI:
10.18653/v1/2020.coling-main.528
Bibkey:
Cite (ACL):
Soham Dan, Hagai Taitelbaum, and Jacob Goldberger. 2020. A Locally Linear Procedure for Word Translation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6013–6018, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
A Locally Linear Procedure for Word Translation (Dan et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2020.coling-main.528.pdf