论文标题
调查诗歌组成系统中的社会偏见
Investigating Societal Biases in a Poetry Composition System
论文作者
论文摘要
越来越多的工作分析和减轻语言理解，产生和检索任务中的社会偏见，尽管研究了创意任务中的偏见仍然没有得到充实的态度。创意语言应用程序是用于与用户直接互动的，因此在这些应用程序中量化和减轻社会偏见很重要。我们介绍了一项有关管道的新研究，以减轻社会偏见，以便在诗歌组成系统中检索下一个经文建议。我们的结果表明，通过情感样式转移的数据扩大有可能减轻社会偏见。
There is a growing collection of work analyzing and mitigating societal biases in language understanding, generation, and retrieval tasks, though examining biases in creative tasks remains underexplored. Creative language applications are meant for direct interaction with users, so it is important to quantify and mitigate societal biases in these applications. We introduce a novel study on a pipeline to mitigate societal biases when retrieving next verse suggestions in a poetry composition system. Our results suggest that data augmentation through sentiment style transfer has potential for mitigating societal biases.
