paper-with-me

Papers

Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis

2020-12-01 · COLING 2020 8 · Michael Lepori

We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases against Black women. We show that these embeddings represent Black women as simultaneously less feminine than White women, and less Black than Black men. This finding aligns with intersectionality theory, which argues that multiple identity categories (such as race or sex) layer on top of each other in order to create unique modes of discrimination that are not shared by any individual category.

📄 PDF Abstract BibTeX

Code (1)

mlepori1/Unequal_Representations 공식 구현 pytorch

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis

2020-11-24 · Michael A. Lepori

We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of inte…

Word Embeddings

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

2020-06-06 · Wei Guo, Aylin Caliskan

With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models ge…

Bias DetectionSentenceWord Embeddings

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

2021-03-05 · Bhavya Ghai, Md Naimul Hoque, Klaus Mueller

Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality, race, disability, religion, etc. A recent study has shown that word embedding models can be laden with biases against …

Word Embeddings

Assessing Social and Intersectional Biases in Contextualized Word Representations

2019-11-04 · NeurIPS 2019 12 · Yi Chern Tan, L. Elisa Celis

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algori…

FairnessSentenceWord Embeddings

The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations

2023-08-03 · Abel Salinas, Parth Vipul Shah, Yuzhong Huang, Robert McCormack 외

Large Language Models (LLMs) have seen widespread deployment in various real-world applications. Understanding these biases is crucial to comprehend the potential downstream consequences when using LLMs to make decisions…