当前位置: X-MOL 学术Science › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Semantics derived automatically from language corpora contain human-like biases
Science ( IF 44.7 ) Pub Date : 2017-04-13 , DOI: 10.1126/science.aal4230
Aylin Caliskan 1 , Joanna J. Bryson 1, 2 , Arvind Narayanan 1
Affiliation  

Machines learn what people know implicitly AlphaGo has demonstrated that a machine can learn how to do things that people spend many years of concentrated study learning, and it can rapidly learn how to do them better than any human can. Caliskan et al. now show that machines can learn word associations from written texts and that these associations mirror those learned by humans, as measured by the Implicit Association Test (IAT) (see the Perspective by Greenwald). Why does this matter? Because the IAT has predictive value in uncovering the association between concepts, such as pleasantness and flowers or unpleasantness and insects. It can also tease out attitudes and beliefs—for example, associations between female names and family or male names and career. Such biases may not be expressed explicitly, yet they can prove influential in behavior. Science, this issue p. 183; see also p. 133 Computers can learn which words go together more or less often and can thus mimic human performance on a test of implicit bias. 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.

中文翻译:

从语言语料库自动派生的语义包含类人偏见

机器学习人们隐含地知道的东西 AlphaGo 已经证明,机器可以学习如何做人们花费多年专注学习的事情,并且它可以快速学会如何比任何人做得更好。卡利斯坎等人。现在表明机器可以从书面文本中学习单词关联,并且这些关联反映了人类学习的关联,由隐式关联测试 (IAT) 衡量(参见 Greenwald 的观点)。为什么这很重要?因为 IAT 在揭示概念之间的关联方面具有预测价值,例如愉快和鲜花或不愉快和昆虫。它还可以梳理出态度和信念——例如,女性姓名与家庭或男性姓名与职业之间的关联。这种偏见可能没有明确表达,但它们可以证明对行为有影响。科学,这个问题 p。183; 另见第。133 计算机可以了解哪些词或多或少地组合在一起,从而可以模仿人类在隐性偏见测试中的表现。机器学习是一种通过发现现有数据中的模式来获得人工智能的方法。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差。我们使用广泛使用的纯统计机器学习模型复制了一系列已知偏差,如隐式关联测试所测量的那样,该模型是在万维网的标准文本语料库上训练的。我们的结果表明,文本语料库包含我们历史偏见的可恢复和准确的印记,无论是对昆虫或花卉的道德中立,还是对种族或性别的问题,甚至只是真实的,反映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。
更新日期:2017-04-13
down
wechat
bug