首页> 外文会议>International symposium on intelligent data analysis >Biased Embeddings from Wild Data: Measuring, Understanding and Removing
【24h】

Biased Embeddings from Wild Data: Measuring, Understanding and Removing

机译:来自野生数据的有偏嵌入:测量,理解和删除

获取原文

摘要

Many modern Artificial Intelligence (AI) systems make use of data embeddings, particularly in the domain of Natural Language Processing (NLP). These embeddings are learnt from data that has been gathered "from the wild" and have been found to contain unwanted biases. In this paper we make three contributions towards measuring, understanding and removing this problem. We present a rigorous way to measure some of these biases, based on the use of word lists created for social psychology applications; we observe how gender bias in occupations reflects actual gender bias in the same occupations in the real world; and finally we demonstrate how a simple projection can significantly reduce the effects of embedding bias. All this is part of an ongoing effort to understand how trust can be built into AI systems.
机译:许多现代人工智能(AI)系统都利用数据嵌入,特别是在自然语言处理(NLP)领域。这些嵌入是从“从野外”收集的数据中获悉的,并且发现它们包含不想要的偏差。在本文中,我们对测量,理解和消除此问题做出了三点贡献。我们使用针对社会心理学应用程序创建的单词表,提出了一种严格的方法来衡量其中一些偏见;我们观察到职业中的性别偏见如何反映现实世界中相同职业中的实际性别偏见;最后,我们演示了简单的投影如何显着降低嵌入偏差的影响。所有这些都是正在进行的努力的一部分,以了解如何将信任构建到AI系统中。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号