气候变化领域集成服务门户(CCPortal): Semantics derived automatically from language corpora contain human-like biases

CCPortal

DOI	10.1126/science.aal4230
	Semantics derived automatically from language corpora contain human-like biases
	Caliskan A.; Bryson J.J.; Narayanan A.
发表日期	2017
ISSN	0036-8075
起始页码	183
结束页码	186
卷号	356 期号:6334
英文摘要	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. © 2017, American Association for the Advancement of Science. All rights reserved.
英文关键词	artificial intelligence; identification method; language; machine learning; numerical model; technological change; Article; cognitive bias; flower; gender; human; insect; Internet; language; machine learning; occupation; priority journal; race; semantics; statistical model; association; female; machine learning; male; nomenclature; sex difference; Hexapoda; Association; Female; Humans; Internet; Language; Machine Learning; Male; Names; Semantics; Sex Factors
语种	英语
来源期刊	Science
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/243216
作者单位	Center for Information Technology Policy, Princeton University, Princeton, NJ, United States; Department of Computer Science, University of Bath, Bath, BA2 7AY, United Kingdom
推荐引用方式 GB/T 7714	Caliskan A.,Bryson J.J.,Narayanan A.. Semantics derived automatically from language corpora contain human-like biases[J],2017,356(6334).
APA	Caliskan A.,Bryson J.J.,&Narayanan A..(2017).Semantics derived automatically from language corpora contain human-like biases.Science,356(6334).
MLA	Caliskan A.,et al."Semantics derived automatically from language corpora contain human-like biases".Science 356.6334(2017).