Gender aware spoken language translation applied to English-Arabic

Abstract

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.

Automatic Gender Identification and Reinflection in Arabic

“…They showed that providing tags that indicate the speaker's gender to the system leads to significant improvements. Similarly, Elaraby et al (2018) marked speaker and listener gender as meta-data input on the source sentence in an English-to-Arabic NMT system. The training data came from OpenSubtitle (Lison and Tiedemann, 2016).…”

“…This paper sits in the intersection of efforts like data augmentation for morphologically rich languages (Zmigrod et al, 2019) and gender-aware MT (Vanmassenhove et al, 2018;Elaraby et al, 2018). Similarly to Zmigrod et al (2019), we are interested in reinflection, but we implement it as character-based NMT.…”

“…Similarly to Zmigrod et al (2019), we are interested in reinflection, but we implement it as character-based NMT. While Vanmassenhove et al (2018) and Elaraby et al (2018) expect gender meta-information as input, we propose a gender-aware post-processing approach, that applies gender identification and reinflection.…”

Multimodal machine translation through visuals and speech

“…In spoken language translation, this line of research into focused evaluations might involve digging into the cases where a good transcript is not enough to disambiguate the translation. One possible case is translating into a language where the speaker's gender matters, such as French or Arabic (Elaraby et al 2018). End-to-end SLT systems have the potential to use non-linguistic information from the speech signal to tackle these challenges, but it is currently unknown to which extent they are able to do so.…”

Extending A Model for Ontology-Based Arabic-English Machine Translation (NAN)

“…These days, there are many types of research that are focusing on the Arabic-English Machine-Translation or something related. Elaraby et al [28], discuss the gender agreement violations as the source of the translation errors. In their opinion, it is not a problem while translating among Arabic, Turkish and Japanese, because a person has many words that point to his/her gender from his/her speech.…”