How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts
Neural Machine Translation systems built on top of Transformer-based architectures are routinely improving the state-of-the-art in translation quality according to word-overlap metrics. However, a growing number of studies also highlight the inherent gender bias that these models incorporate during training, which reflects poorly in their translations. In this work, we investigate whether these models can be instructed to fix their bias during inference using targeted, guided instructions as contexts. By translating relevant contextual sentences during inference along with the input, we observe large improvements in reducing the gender bias in translations, across three popular test suites (WinoMT, BUG, SimpleGen). We further propose a novel metric to assess several large pre-trained models (OPUS-MT, M2M-100) on their sensitivity towards using contexts during translation to correct their biases. Our approach requires no fine-tuning and thus can be used easily in production systems to de-bias translations from stereotypical gender-occupation bias 1. We hope our method, along with our metric, can be used to build better, bias-free translation systems.
Code (1)
Tasks
Bias DetectionMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Mitigating 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 TranslationTranslationSentiment Aware Neural Machine Translation
Sentiment ambiguous lexicons refer to words where their polarity depends strongly on con- text. As such, when the context is absent, their translations or their embedded sentence ends up (incorrectly) being dependent on …
Machine TranslationNMTSentenceTranslation+1How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation
Large language models (LLMs) have demonstrated strong performance in general-purpose machine translation, but their effectiveness in complex, domain-sensitive translation tasks remains underexplored. Recent advancements …
Machine TranslationTranslationDetecting and Mitigating Bias by Treating Fairness as a Symmetry Operation
Machine learning systems deployed in high stakes socioeconomic settings routinely display bias. We formalize bias as a symmetry breaking operation: a classifier is fair if its outputs remain invariant under the counterfa…