Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection

Amit Moryossef, Roee Aharoni, Yoav Goldberg


Abstract
When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must “guess” this missing information, often leading to incorrect translations in the given context. We propose a black-box approach for injecting the missing information to a pre-trained neural machine translation system, allowing to control the morphological variations in the generated translations without changing the underlying model or training data. We evaluate our method on an English to Hebrew translation task, and show that it is effective in injecting the gender and number information and that supplying the correct information improves the translation accuracy in up to 2.3 BLEU on a female-speaker test set for a state-of-the-art online black-box system. Finally, we perform a fine-grained syntactic analysis of the generated translations that shows the effectiveness of our method.
Anthology ID:
W19-3807
Volume:
Proceedings of the First Workshop on Gender Bias in Natural Language Processing
Month:
August
Year:
2019
Address:
Florence, Italy
Venues:
ACL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
49–54
Language:
URL:
https://aclanthology.org/W19-3807
DOI:
10.18653/v1/W19-3807
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/W19-3807.pdf