Spoken Language Translation (SLT) is becoming more widely used and becoming a communication tool that helps in crossing language barriers. One of the challenges of SLT is the translation from a language without gender agreement to a language with gender agreement such as English to Arabic. In this paper, we introduce an approach to tackle such limitation by enabling a Neural Machine Translation system to produce gender-aware translation. We show that NMT system can model the speaker/listener gender information to produce gender-aware translation. We propose a method to generate data used in adapting a NMT system to produce gender-aware. The proposed approach can achieve significant improvement of the translation quality by 2 BLEU points.
@article{arxiv.1802.09287,
title = {Gender Aware Spoken Language Translation Applied to English-Arabic},
author = {Mostafa Elaraby and Ahmed Y. Tawfik and Mahmoud Khaled and Hany Hassan and Aly Osama},
journal= {arXiv preprint arXiv:1802.09287},
year = {2018}
}
Comments
Proceedings of the Second International Conference on Natural Language and Speech Processing, 2018 IEEE