Gender Aware Spoken Language Translation Applied to English-Arabic
This addresses gender agreement issues in translation for languages like Arabic, though it appears incremental as it builds on existing NMT systems.
The paper tackles the challenge of translating from English (no gender agreement) to Arabic (gender agreement) in spoken language translation by enabling neural machine translation systems to produce gender-aware translations. The proposed method achieves a 2 BLEU point improvement in translation quality.
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.