Understanding Undesirable Word Embedding Associations (P19-1)

Copied to clipboard

Challenge: Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes.
Approach: They propose to use subspace projection to debias vectors post hoc using a model that implicitly does matrix factorization to debunk gender bias.
Outcome: The proposed test overestimates gender bias in word embeddings by using subspace projection, a method that is widely used in training.

Similar Papers

Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to debias word embeddings from human-generated corpora inherit strong gender bias . prior work has suggested removing gender component from pre-trained word embeds or compressing gender information into a few dimensions of the embeddable space .
Approach: They propose a technique that purifies word embeddings against inferred gender subspaces . they propose to preserve distributional semantics of pre-trained word embeds while reducing gender bias .
Outcome: The proposed technique preserves distributional semantics of pre-trained word embeddings while reducing gender bias to a larger degree than prior approaches.
Querying Word Embeddings for Similarity and Relatedness (N18-1)

Copied to clipboard

Challenge: Word2Vec embeddings have become popular representations of word meaning . similarity between two words is often assumed to be a direction-less measure, whereas relatedness is inherently directional.
Approach: They propose to use word embeddings to predict asymmetric association between words from a dataset of production norms to generate thematically related words.
Outcome: The proposed model predicts asymmetric association between words from a recently published dataset of production norms.
Exploring Human Gender Stereotypes with Word Association Test (D19-1)

Copied to clipboard

Challenge: Existing word embeddings have been used to study gender stereotypes in texts . however, evaluating their validities is still an open problem . et al.: this study investigates gender bias using the lens of language, especially, the words .
Approach: They use word association test to derive bias scores for large amount of words . they find that these bias scores correlate well with bias in the real world .
Outcome: The proposed method correlates well with bias in the real world, and with census data, it provides a different perspective on gender stereotypes in words.
The Undesirable Dependence on Frequency of Gender Bias Metrics Based on Word Embeddings (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have found word embeddings can capture semantic similarity but may be affected by word frequency.
Approach: They find that word embeddings can capture semantic similarity but may be affected by word frequency . they compare this effect with an alternative metric based on Pointwise Mutual Information .
Outcome: The proposed method does not depend on word frequency, but it does return female bias in low frequency words.
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.
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.
Identifying and Reducing Gender Bias in Word-Level Language Models (N19-3)

Copied to clipboard

Challenge: Existing discriminatory biases in training data can be amplified by models . text corpora exhibit socially problematic biase .
Approach: They propose a metric to measure gender bias and a regularization loss term to minimize embeddings onto an embeddable subspace that encodes gender.
Outcome: The proposed method reduces gender bias up to an optimal weight assigned to the loss term, and the model becomes unstable as the perplexity increases.
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods to mitigate stereotypical biases by linear projection are too aggressive . existing methods remove bias, but they also erase valuable information from word embeddings .
Approach: They propose a bias-mitigating method that disentangles biased associations between concepts instead of removing concepts wholesale.
Outcome: The proposed method disentangles biased associations between concepts rather than eliminating concepts wholesale.
Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for gender bias mitigation for word embeddings are based on pre-trained word embeds . however, the assumption that the bias subspace is linear is untested .
Approach: They propose a method to isolate gender bias in word embeddings using pre-trained word embeds.
Outcome: The proposed method eliminates gender bias in word embeddings but assumes bias subspace is linear . the proposed method has some drawbacks, but it is a good one for a non-linear analysis.
Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them (N19-1)

Copied to clipboard

Challenge: Existing methods to remove gender bias from word embeddings are insufficient, we argue . existing methods for gender-neutral modeling are ineffective, we conclude .
Approach: They propose methods to reduce gender bias in word embeddings by debiasing them using text corpora.
Outcome: The proposed methods show that they can reduce gender bias in word embeddings . the proposed methods are insufficient and should not be trusted, the authors argue .

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