Language (Technology) is Power: A Critical Survey of "Bias" in NLP release_nyzr4fj5gne55jzhzm2fy5xeqa

by Su Lin Blodgett and Solon Barocas and Hal Daumé III and Hanna Wallach

Released as a article .

2020  

Abstract

We survey 146 papers analyzing "bias" in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing "bias" is an inherently normative process. We further find that these papers' proposed quantitative techniques for measuring or mitigating "bias" are poorly matched to their motivations and do not engage with the relevant literature outside of NLP. Based on these findings, we describe the beginnings of a path forward by proposing three recommendations that should guide work analyzing "bias" in NLP systems. These recommendations rest on a greater recognition of the relationships between language and social hierarchies, encouraging researchers and practitioners to articulate their conceptualizations of "bias"---i.e., what kinds of system behaviors are harmful, in what ways, to whom, and why, as well as the normative reasoning underlying these statements---and to center work around the lived experiences of members of communities affected by NLP systems, while interrogating and reimagining the power relations between technologists and such communities.
In text/plain format

Archived Files and Locations

application/pdf  560.6 kB
file_6ietxvj33zhavmgjsgmuqnmo7u
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-05-29
Version   v2
Language   en ?
arXiv  2005.14050v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 79b2641c-d264-4d29-8ac6-5493ac8c1482
API URL: JSON