Construct · 1 fields · 1 citations

word embedding bias: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Algorithmic fairness

human-like stereotypes about gender and race that machine-learned word representations absorb from ordinary text, measurable with an association test modeled on the IAT.

In algorithmic fairness, word embedding bias refers to human-like stereotypes about gender and race that machine-learned word representations absorb from ordinary text, measurable with an association test modeled on the IAT. This meaning comes from Caliskan (2017) in Science.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how word embedding bias sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

association4 fields · 4 citationsjingle · one word, four constructs bias6 fields · 8 citationsjingle · one name, six constructs embedding2 fields · 3 citationsjingle · one word, two constructs

References

Caliskan, A., Bryson, J. J., & Narayanan, A. (2017). Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334), 183-186. https://doi.org/10.1126/science.aal4230

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct