Semantics derived automatically from language corpora necessarily contain human biases

Here is a draft of the paper I promised last month:

Aylin Caliskan-Islam, Joanna J. Bryson, & Arvind Narayanan, Semantics derived automatically from language corpora necessarily contain human biases.

This draft was submitted to arxiv 24 August, and released there 26 August; we are working on a journal submission as well.

Meaning really is no more or less than how a word is used, so AI absorbs true meaning, including prejudice.  We demonstrate this empirically.  This is an extension of my research programme into semantics originally deriving from my interest in the origins of human cognition, but now with help from the awesome researchers at Princeton I've merged this with my AI ethics work, and also managed to pitch for cognitive systems approaches to AI.



0