Five sources of bias in natural language processing
Language and Linguistics Compass · 2021-08 · 15 (8)
DOI: 10.1111/lnc3.12432 ↗Kurz gefasst
Fachartikel in der Zeitschrift Language and Linguistics Compass, online erschienen am 20.08.2021. Verfasst von Dirk Hovy und 1 weiteren Autor:innen. Beteiligte Einrichtung: Marketing Department Bocconi University Milan Italy. Die Arbeit wurde bisher 240-mal zitiert (Crossref) und nennt 116 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: H2020 European Research Council.
Abstract (Originalsprache)
Recently, there has been an increased interest in demographically grounded bias in natural language processing (NLP) applications. Much of the recent work has focused on describing bias and providing an overview of bias in a larger context. Here, we provide a simple, actionable summary of this recent work. We outline five sources where bias can occur in NLP systems: (1) the data, (2) the annotation process, (3) the input representations, (4) the models, and finally (5) the research design (or how we conceptualize our research). We explore each of the bias sources in detail in this article, including examples and links to related work, as well as potential counter‐measures.
Autor:innen und Institutionen
- Marketing Department Bocconi University Milan Italy.
- School of Computer Science Carnegie Mellon University Pittsburgh Pennsylvania USA.
Förderung
- H2020 European Research Council
Zitieren
APA
Hovy, D., & Prabhumoye, S. (2021). Five sources of bias in natural language processing. Language and Linguistics Compass, 15(8). https://doi.org/10.1111/lnc3.12432
Vancouver
Hovy D, Prabhumoye S. Five sources of bias in natural language processing. Language and Linguistics Compass. 2021;15(8). doi:10.1111/lnc3.12432
BibTeX
@article{Hovy2021,
author = {Hovy, Dirk and Prabhumoye, Shrimai},
title = {Five sources of bias in natural language processing},
journal = {Language and Linguistics Compass},
year = {2021},
volume = {15},
number = {8},
doi = {10.1111/lnc3.12432}
}
EUVIMED