Multilingual word translation using auxiliary languages

Hagai Taitelbaum, Gal Chechik, Jacob Goldberger


Abstract
Current multilingual word translation methods are focused on jointly learning mappings from each language to a shared space. The actual translation, however, is still performed as an isolated bilingual task. In this study we propose a multilingual translation procedure that uses all the learned mappings to translate a word from one language to another. For each source word, we first search for the most relevant auxiliary languages. We then use the translations to these languages to form an improved representation of the source word. Finally, this representation is used for the actual translation to the target language. Experiments on a standard multilingual word translation benchmark demonstrate that our model outperforms state of the art results.
Anthology ID:
D19-1134
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:
1330–1335
Language:
URL:
https://aclanthology.org/D19-1134
DOI:
10.18653/v1/D19-1134
Bibkey:
Cite (ACL):
Hagai Taitelbaum, Gal Chechik, and Jacob Goldberger. 2019. Multilingual word translation using auxiliary languages. 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 1330–1335, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Multilingual word translation using auxiliary languages (Taitelbaum et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1134.pdf