ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translation

Javier García Gilabert,Carlos Escolano,Marta R. Costa-Jussà

CoRR(2023)

引用 0|浏览21
暂无评分
摘要
Our proposed method, ReSeTOX (REdo SEarch if TOXic), addresses the issue of Neural Machine Translation (NMT) generating translation outputs that contain toxic words not present in the input. The objective is to mitigate the introduction of toxic language without the need for re-training. In the case of identified added toxicity during the inference process, ReSeTOX dynamically adjusts the key-value self-attention weights and re-evaluates the beam search hypotheses. Experimental results demonstrate that ReSeTOX achieves a remarkable 57% reduction in added toxicity while maintaining an average translation quality of 99.5% across 164 languages.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络