Challenge: Recent work has relied on word embedding bias measures, such as WEAT, but these methods can be inaccurate due to several representation issues, such low-resource settings and token frequency differences.
Approach: They propose to use WEAT to quantify social bias in US online news articles and embed embedding algorithms to account for the aforementioned issues.
Outcome: The proposed algorithms do not match the literature, but they reduce the gap.

Similar Papers

When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People? (2020.acl-main)

Copied to clipboard

Challenge: a study of word embeddings shows that social biases are more accurate than survey data for some dimensions of meaning.
Approach: a new study investigates the extent to which word embeddings accurately reflect biases . they find that biased word embeds mirror survey data across 17 dimensions of social meaning .
Outcome: a new study shows that word embeddings accurately reflect biases on average across dimensions of social meaning . biased embedders are more reflective of survey data for some dimensions of meaning than others, the study finds .
Measuring Social Biases in Grounded Vision and Language Embeddings (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods to measure social biases in word embeddings are limited to visually grounded word embeds . a new study generalizes word embedment associations to visually ground word embeddas .
Approach: They generalize word embeddings' biases to visually grounded word embeds . they propose two generalizations that answer questions about how biase, language, and vision interact .
Outcome: The proposed measures are applied to a new dataset that includes 10,228 images from COCO, Conceptual Captions, and Google Images.
SOS: Systematic Offensive Stereotyping Bias in Word Embeddings (2022.coling-1)

Copied to clipboard

Challenge: Systematic Offensive Stereotyping (SOS) in word embeddings could lead to associating marginalised groups with hate speech and profanity.
Approach: They propose a quantitative measure of the systematic offensive stereotyping (SOS) in word embeddings and validate it in most commonly used word embeds.
Outcome: The proposed measure correlates with published statistics on online extremism, but does not explain hate speech detection models.
Sense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense Embeddings (2022.acl-long)

Copied to clipboard

Challenge: Existing studies have evaluated social biases in word embeddings, but they are understudied.
Approach: They propose to evaluate the social biases in sense embeddings using a benchmark dataset for word embedders.
Outcome: The proposed measures show that even when no biases are found at word-level, there are still worrying levels of social biase at sense-level which are often ignored by the word- level bias evaluation measures.
Robustness and Reliability of Gender Bias Assessment in Word Embeddings: The Role of Base Pairs (2020.aacl-main)

Copied to clipboard

Challenge: Existing methods to quantify gender bias in word embeddings are not robust and cannot identify common types of bias.
Approach: They propose to quantify gender bias by using cosine similarity to a pair of gender words and using analogies.
Outcome: The proposed methods are not robust and cannot identify common types of bias, while analogies are unsuitable indicators.
A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings (P19-1)

Copied to clipboard

Challenge: Word embeddings suffer from unintended demographic biases, a new study shows . word embedders can cause downstream NLP systems to be unfair, the authors argue .
Approach: They propose a metric to evaluate the fairness of word embeddings via the relative negative sentiment associated with demographic identity terms from various protected groups.
Outcome: The proposed metric measures fairness in word embeddings via the relative negative sentiment associated with demographic identity terms from various protected groups.
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings (2025.coling-main)

Copied to clipboard

Challenge: Existing work in this field has looked most commonly into gender bias, racial bias, and religious bias.
Approach: They propose an algorithm that uses a neural network to perform ‘soft debiasing’ and build on the seminal work of (CITATION) and (CitATION).
Outcome: The proposed algorithm outperforms current methods on gender, race, and religion metrics on a wide range of metrics.
Discovering Biased News Articles Leveraging Multiple Human Annotations (2020.lrec-1)

Copied to clipboard

Challenge: Political propaganda and one-sided views can be found in the news and can cause distrust in media.
Approach: They propose to annotate politically biased news articles by an algorithm annotated by domain experts and crowd workers and to compare them to crowd workers.
Outcome: The proposed method compares domain experts to crowd workers and shows that bias can be detected automatically.
On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach (2023.acl-short)

Copied to clipboard

Challenge: Word embeddings have been used to quantify biases in texts for years, but their statistical properties and advantages have not been studied.
Approach: They propose to use PMI-based metric to quantify bias in corpora by conditional probabilities and odds ratio to approximate it.
Outcome: The proposed measure can be approximated by an odds ratio, which makes statistical inferences cost-effective and meaningful.
Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings (N19-1)

Copied to clipboard

Challenge: Existing methods to debias word embeddings in binary settings such as gender and religion are limited to binary labels, whereas word2vec embedders can be used to propagate biases.
Approach: They propose a method to debias word embeddings in multiclass settings such as gender and religion, extending the work of Bolukbasi et al. (2016).
Outcome: The proposed method maintains the efficacy in standard NLP tasks while maintaining the utility of embeddings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations