Semantics derived automatically from language corpora necessarily contain human biases

Add to your list(s) Download to your calendar using vCal

• Arvind Narayanan, Princeton University
• Tuesday 11 October 2016, 14:00-15:00
• LT2, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Laurent Simon.

Abstract: Joint work with Aylin Caliskan-Islam and Joanna J. Bryson

Artificial intelligence and machine learning are in a period of astounding growth. However, there are concerns that these technologies may be used, either with or without intention, to perpetuate the prejudice and unfairness that unfortunately characterizes many human institutions. Here we show for the first time that human-like semantic biases result from the application of standard machine learning to ordinary language—-the same sort of language humans are exposed to every day. We replicate a spectrum of standard human biases as exposed by the Implicit Association Test and other well-known psychological studies. We replicate these using a widely used, purely statistical machine-learning model—-namely, the GloVe word embedding—-trained on a corpus of text from the Web. Our results indicate that language itself contains recoverable and accurate imprints of our historic biases, whether these are morally neutral as towards insects or flowers, problematic as towards race or gender, or even simply veridical, reflecting the status quo for the distribution of gender with respect to careers or first names. These regularities are captured by machine learning along with the rest of semantics. In addition to our empirical findings concerning language, we also contribute new methods for evaluating bias in text, the Word Embedding Association Test (WEAT) and the Word Embedding Factual Association Test (WEFAT). Our results have implications not only for AI and machine learning, but also for the fields of psychology, sociology, and human ethics, since they raise the possibility that mere exposure to everyday language can account for the biases we replicate here.

Link to paper: https://arxiv.org/abs/1608.07187

Bio: Arvind Narayanan is an Assistant Professor of Computer Science at Princeton. He leads the Princeton Web Transparency and Accountability Project to uncover how companies collect and use our personal information. Narayanan also leads a research team investigating the security, anonymity, and stability of cryptocurrencies as well as novel applications of blockchains. He co-created a Massive Open Online Course as well as a textbook on Bitcoin and cryptocurrency technologies. His doctoral research showed the fundamental limits of de-identification, for which he received the Privacy Enhancing Technologies Award.

Narayanan is an affiliated faculty member at the Center for Information Technology Policy at Princeton and an affiliate scholar at Stanford Law School’s Center for Internet and Society.

This talk is part of the Computer Laboratory Security Seminar series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Computer Laboratory Security Seminar
• Department of Computer Science and Technology talks and seminars
• Interested Talks
• LT2, Computer Laboratory, William Gates Building
• School of Technology
• Security-related talks
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.