arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.05459cs.CLcs.SI
收藏

一种减轻多语言文本分类中性别偏见的简单自适应方法

Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification

University of Memphis(孟菲斯大学)

Xiaolei Huang

摘要:

现有的方法,以减轻人口偏见的单语数据进行评估,但是,多语种数据尚未进行检查。在这项工作中,我们将性别视为域(例如,男性与女性)的区别,并提出了一个标准的领域自适应模型,以减少性别偏见,提高文本分类器在多语言环境下的性能。我们评估我们的方法在两个文本分类任务,仇恨言论检测和评级预测,并证明我们的方法的有效性与三个公平意识的基线。

英文摘要:

Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation model to reduce the gender bias and improve performance of text classifiers under multilingual settings. We evaluate our approach on two text classification tasks, hate speech detection and rating prediction, and demonstrate the effectiveness of our approach with three fair-aware baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑