Journal
COMPUTATIONAL LINGUISTICS
Volume 46, Issue 2, Pages 487-498Publisher
MIT PRESS
DOI: 10.1162/coli_a_00379
Keywords
-
Ask authors/readers for more resources
Analogies such asman is to king as woman is to Xare often used to illustrate the amazing power of word embeddings. Concurrently, they have also been used to expose how strongly human biases are encoded in vector spaces trained on natural language, with examples likeman is to computer programmer as woman is to homemaker. Recent work has shown that analogies are in fact not an accurate diagnostic for bias, but this does not mean that they are not used anymore, or that their legacy is fading. Instead of focusing on the intrinsic problems of the analogy task as a bias detection tool, we discuss a series of issues involving implementation as well as subjective choices that might have yielded a distorted picture of bias in word embeddings. We stand by the truth that human biasesarepresent in word embeddings, and, of course, the need to address them. But analogies are not an accurate tool to do so, and the way they have been most often used has exacerbated some possibly non-existing biases and perhaps hidden others. Because they are still widely popular, and some of them have become classics within and outside the NLP community, we deem it important to provide a series of clarifications that should put well-known, and potentially new analogies, into the right perspective.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available