Center for Information Technology Policy, Princeton University, Princeton, NJ, USA.
Department of Computer Science, University of Bath, Bath BA2 7AY, UK.
Science. 2017 Apr 14;356(6334):183-186. doi: 10.1126/science.aal4230.
Machine learning is a means to derive artificial intelligence by discovering patterns in existing data. Here, we show that applying machine learning to ordinary human language results in human-like semantic biases. We replicated a spectrum of known biases, as measured by the Implicit Association Test, using a widely used, purely statistical machine-learning model trained on a standard corpus of text from the World Wide Web. Our results indicate that text corpora contain recoverable and accurate imprints of our historic biases, whether morally neutral as toward insects or flowers, problematic as toward race or gender, or even simply veridical, reflecting the status quo distribution of gender with respect to careers or first names. Our methods hold promise for identifying and addressing sources of bias in culture, including technology.
机器学习是通过发现现有数据中的模式来获得人工智能的一种手段。在这里，我们表明，将机器学习应用于普通人类语言会导致类似人类的语义偏见。我们使用广泛使用的、仅基于统计的机器学习模型，该模型基于来自万维网的标准文本语料库进行训练，复制了一系列已知的偏见，这些偏见是通过内隐联想测试来衡量的。我们的结果表明，文本语料库包含可恢复和准确的历史偏见印记，无论是对昆虫或花朵等道德中立的偏见，还是对种族或性别等有问题的偏见，甚至是简单的真实性偏见，反映了性别在职业或名字方面的现状分布。我们的方法有望识别和解决文化中的偏见来源，包括技术。
