Papers with bias mitigation techniques

7 papers
Studying and Mitigating Biases in Sign Language Understanding Models (2024.emnlp-main)

Copied to clipboard

Challenge: Using crowd-sourced sign language datasets to reduce performance disparities is critical to addressing potential biases and inequities.
Approach: They use demographic information to study biases that may result from models trained on crowd-sourced sign datasets.
Outcome: The proposed approach reduces performance disparities without decreasing accuracy.
EcoSpeak: Cost-Efficient Bias Mitigation for Partially Cross-Lingual Speaker Verification (2024.findings-naacl)

Copied to clipboard

Challenge: Linguistic bias is a critical problem that harms the diversity, equity, and inclusiveness of Natural Language Processing tools.
Approach: They propose a low-cost solution that incorporates contrastive linguistic attention to emphasize relevant speaker verification embedding parts.
Outcome: The proposed model is able to mitigate linguistic bias in five partially cross-lingual scenarios.
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models (2022.acl-long)

Copied to clipboard

Challenge: Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on.
Approach: They propose to use Counterfactual Data Augmentation, Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebia as bias mitigation techniques to quantify their effectiveness.
Outcome: The proposed techniques are Counterfactual Data Augmentation (CDA), Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebia.
Towards Understanding Gender Bias in Relation Extraction (2020.acl-main)

Copied to clipboard

Challenge: Existing bias mitigation techniques have a negative effect on NRE, a study finds .
Approach: They create a dataset to analyze gender bias in relation extraction systems . they find that existing bias mitigation techniques have a negative effect on NRE .
Outcome: The proposed dataset analyzes gender bias in relation extraction systems using a 10% human annotated test set.
Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Social biases present in data are often directly reflected in the predictions of models trained on that data.
Approach: They analyze gender bias in dialogue data and propose techniques to mitigate it . they use counterfactual data augmentation, targeted data collection, and bias controlled training .
Outcome: The proposed techniques mitigate gender bias by balancing genderedness of generated dialogue utterances.
Balancing out Bias: Achieving Fairness Through Balanced Training (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to reducing group bias do not account for correlations between author demographics and linguistic variables, limiting their effectiveness.
Approach: They extend a method for countering group bias using balanced training by balancing each demographic group in training and using protected attributes as input.
Outcome: The proposed model outperforms all other methods when combined with balanced training.
Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation (2023.emnlp-main)

Copied to clipboard

Challenge: Gender bias is a significant issue in machine translation, but most studies focus on debiasing bilingual models without consideration for multilingual systems.
Approach: They propose a method which debiases bilingual models for unambiguous cases where there is a single correct translation.
Outcome: The proposed method improves gender accuracy by a wide margin without hampering translation performance.

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