How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts. (arXiv:2205.10762v2 [cs.CL] UPDATED)

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, …

arxiv bias gender gender bias machine machine translation neural machine translation systems translation