Added toxicity in the context of translation refers to the fact of producing
a translation output with more toxicity than there exists in the input. In this
paper, we present MinTox which is a novel pipeline to identify added toxicity
and mitigate this issue which works at inference time. MinTox uses a toxicity
detection classifier which is multimodal (speech and text) and works in
languages at scale. The mitigation method is applied to languages at scale and
directly in text outputs. MinTox is applied to SEAMLESSM4T, which is the latest
multimodal and massively multilingual machine translation system. For this
system, MinTox achieves significant added toxicity mitigation across domains,
modalities and language directions. MinTox manages to approximately filter out
from 25% to 95% of added toxicity (depending on the modality and domain) while
keeping translation quality.

MinTox 是一个新颖的流水线，用于识别和减轻翻译中的增加毒性问题，并在推理时工作。MinTox 使用多模态的毒性检测分类器，并在规模化和直接的文本输出中应用于多语言。在 SEAMLESSM4T 系统中，MinTox 实现了领域、模态和语言方向的显著毒性缓解，从而滤除了 25% 至 95% 的增加毒性，同时保持翻译质量。