Gender-Aware Reinflection using Linguistically Enhanced Neural Models

How researchers see this paper

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

Societal Biases in Language Generation: Progress and Challenges (2021, methodology): “Studies of gender bias in machine translation are well-suited to evaluations using absolute scores: many use BLEU and its variants to evaluate correct gender inflections and translations (Moryossef et al., 2019; Escudé Font and Costajussà, 2019; Elaraby et al., 2018; Habash et al., 2019; Alhafni et ”
Gender Bias in Machine Translation (2021, background): “In (Alhafni et al., 2020), the preferred gender of the speaker and the translated Arabic sentence are fed to that component, which re-inflects the sentence in the desired form.”
Perturbation Augmentation for Fairer NLP (2022, methodology): “…gender, has already been used to combat bias arising from morphological underspecifi-cation during automatic translation for languages with more grammatical gender morphology than English, including Arabic (Habash et al., 2019; Alhafni et al., 2020) and Italian (Vanmassenhove and Monti, 2021).”
First the Worst: Finding Better Gender Translations During Beam Search (2021, background): “Related approaches083 for monolingual tasks reinflect whole-sentence gen-084 der (Habash et al., 2019; Alhafni et al., 2020; Sun085 et al., 2021).”