Learning Translations via Matrix Completion

Derry Tanti Wijaya, Brendan Callahan, John Hewitt, Jie Gao, Xiao Ling, Marianna Apidianaki, Chris Callison-Burch


Abstract
Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages.
Anthology ID:
D17-1152
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1452–1463
Language:
URL:
https://aclanthology.org/D17-1152
DOI:
10.18653/v1/D17-1152
Bibkey:
Cite (ACL):
Derry Tanti Wijaya, Brendan Callahan, John Hewitt, Jie Gao, Xiao Ling, Marianna Apidianaki, and Chris Callison-Burch. 2017. Learning Translations via Matrix Completion. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1452–1463, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Learning Translations via Matrix Completion (Wijaya et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1152.pdf