Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings

Domaine:

natural language processing

Type de record:

paperdataset
Créateur:
LauTakPonGla
Hôte:avatar
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. accepted for WANLP 20

Visit

arxiv.org

Tasks

embeddings

Tags

Computation and Language

Similaires

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like BiasesWordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word EmbeddingsDetecting gender bias in Arabic text through word embeddingsDiaLex: A Benchmark for Evaluating Multidialectal Arabic Word EmbeddingsDocument embeddings for Arabic Sentiment AnalysisisiZulu Word Embeddings

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases

With the starting point that implicit human biases are reflected in the statistical regularities of

WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings

Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality

Detecting gender bias in Arabic text through word embeddings

International audience For generations, women have fought to achieve equal rights wit

DiaLex: A Benchmark for Evaluating Multidialectal Arabic Word Embeddings

Word embeddings are a core component of modern natural language processing systems, making the ability to thoroughly evaluate them a vital task. We describe DiaLex, a benchmark for intrinsic evaluation of dialectal Arabic word embedding. DiaLex covers five importan

Document embeddings for Arabic Sentiment Analysis

International audience Research and industry are more and more focusing in finding au

isiZulu Word Embeddings