AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings

Anne Lauscher · Rafik Takieddin · Simone Paolo Ponzetto · Goran Glavaš

19 citations0/0 files storedMADOC (University of Mannheim)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Topic Modeling Hate Speech and Cyberbullying Detection

Abstract

Recent work has shown that distributional word vector spaces often encode human biases like sexism or racism. In this work, we conduct an extensive analysis of biases in Arabic word embeddings by applying a range of recently introduced bias tests on a variety of embedding spaces induced from corpora in Arabic. We measure the presence of biases across several dimensions, namely: embedding models (Skip-Gram, CBOW, and FastText) and vector sizes, types of text (encyclopedic text, and news vs. user-generated content), dialects (Egyptian Arabic vs. Modern Standard Arabic), and time (diachronic analyses over corpora from different time periods). Our analysis yields several interesting findings, e.g., that implicit gender bias in embeddings trained on Arabic news corpora steadily increases over time (between 2007 and 2017). We make the Arabic bias specifications (AraWEAT) publicly available.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 19 citations exist upstream.

References

2017Semantics derived automatically from language corpora contain human-like biases 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings 2002Harvesting implicit group attitudes and beliefs from a demonstration web site.2020Language (Technology) is Power: A Critical Survey of “Bias” in NLP 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them 2019Understanding Undesirable Word Embedding Associations 2019It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution 2019Attenuating Bias in Word Vectors

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.