Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information

By Christine Basta, Marta Ruiz Costa-jussà, José A. R. Fonollosa. 2020

33 citations recorded by the source corpus.

Gender bias negatively impacts many natural language processing applications, including machine translation (MT). The motivation behind this work is to study whether recent proposed MT techniques are significantly contributing to attenuate biases in document-level and gender-balanced data. For the study, we consider approaches of adding the previous sentence and the speaker information, implemented in a decoder-based neural MT system. We show improvements both in translation quality (+1 BLEU point) as well as in gender bias mitigation on WinoMT (+5% accuracy).

Subfields: Artificial Intelligence, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Societal Biases in Language Generation: Progress and Challenges (2021, methodology): “The second category is methods that attach a short prefix at training time (Vanmassenhove et al., 2018; Basta et al., 2020; Alhafni et al., 2020) or inference time (Moryossef et al., 2019).”
Fine-tuning Neural Machine Translation on Gender-Balanced Datasets (2020, methodology): “Previous research in the area of NMT has proposed to either mitigate biases using debiased word embeddings (Font and Costa-juss`a, 2019) and using contextual information (Basta et al., 2020) or evaluating and measuring the amount of bias present in the translation (Stanovsky et al., 2019).”