Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information
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).
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderMachine TranslationSentenceTranslationSimilar Papers 제목 키워드 기반
Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages. In this paper, and from an algorithmic perspective, we explore if the chosen architectu…
DecoderMachine TranslationTranslationMitigating Gender Bias in Machine Translation through Adversarial Learning
Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary res…
Machine TranslationTranslationMitigating Gender Bias in Machine Translation through Adversarial Learning
Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary res…
Machine TranslationTranslationGender Bias in Machine Translation and The Era of Large Language Models
This chapter examines the role of Machine Translation in perpetuating gender bias, highlighting the challenges posed by cross-linguistic settings and statistical dependencies. A comprehensive overview of relevant existin…
FairnessMachine TranslationTranslationMulti-Task Learning for Improving Gender Accuracy in Neural Machine Translation
Machine Translation is highly impacted by social biases present in data sets, indicating that it reflects and amplifies stereotypes. In this work, we study mitigating gender bias by jointly learning the translation, the …
Machine TranslationMulti-Task LearningTranslation