Science· 2017Q1
Semantics derived automatically from language corpora contain human-like biases
- 2,826citations
- Q1SCImago
- 2017year
Short summary
A machine learning model trained on web text replicated human-like biases, including those related to race and gender, as measured by the Implicit Association Test.
AI-generated from the title and abstract; the full text is not read.
Key points
- Machine learning models trained on web text exhibit human-like semantic biases.
- These biases were measured using the Implicit Association Test and replicated by a statistical model.
- Text corpora contain recoverable imprints of historical biases related to gender, race, and other categories.
- The methods can help identify and address sources of bias in culture and technology.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source. Science, 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Cognitive Neuroscience
Cognitive NeuroscienceNeuroscience