Gender-Aware Natural Language Translation

By James Kuczmarski, Melvin Johnson. 2018

25 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Carbon Emissions and Large Neural Network Training (2021, background): “Creating such models requires careful attention to issues of fairness and bias [Ben21, Gar19, Joh20, Kuc18, Mer19], but they also have the potential to benefit people everywhere.”
Tagged Back-Translation (2019, background): “Kuczmarski and Johnson (2018) use tags to control gender in translation.”
On Measuring Gender Bias in Translation of Gender-neutral Pronouns (2019, background): “In Kuczmarski and Johnson (2018), the paper mainly aims to perform post-processing that yields gender nonbiased result in pronoun translation for Turkish, but no specific description of the evaluation was accompanied.”
They, Them, Theirs: Rewriting with Gender-Neutral English (2021, background): “If there is no disambiguating information available, providing multiple alternatives (Kuczmarski and Johnson, 2018) with a genderneutral translation might be more appropriate.”
Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters (2020, background): “Machine translation has been shown to exhibit gender bias (Prates et al., 2020), and several solutions have already been proposed to mitigate it (Kuczmarski and Johnson, 2018; Font and Costa-jussà, 2019; Costa-jussà and de Jorge, 2020).”
Translationese as a Language in “Multilingual” NMT (2019, background): “, 2016a), gender from a gender-neutral language (Kuczmarski and Johnson, 2018), as well as to”