Good, but not always Fair: An Evaluation of Gender Bias for three commercial Machine Translation Systems

arXiv:2306.05882v2 Announce Type: replace
Abstract: Machine Translation (MT) continues to make significant strides in quality and is increasingly adopted on a larger scale. Consequently, analyses have been redirected to more nuanced aspects, intricate phenomena, as well as potential risks that may arise from the widespread use of MT tools. Along this line, this paper offers a meticulous assessment of three commercial MT systems - Google Translate, DeepL, and Modern MT - with a specific focus on gender translation and bias. …

abstract arxiv bias commercial cs.cl evaluation fair gender gender bias good machine machine translation quality risks scale systems translation type