Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability
–arXiv.org Artificial Intelligence
The burgeoning field of Natural Language Processing (NLP) stands at a critical juncture where the integration of fairness within its frameworks has become an imperative. This PhD thesis addresses the need for equity and transparency in NLP systems, recognizing that fairness in NLP is not merely a technical challenge but a moral and ethical necessity, requiring a rigorous examination of how these technologies interact with and impact diverse human populations. Through this lens, this thesis undertakes a thorough investigation into the development of equitable NLP methodologies and the evaluation of biases that prevail in current systems. First, it introduces an innovative algorithm to mitigate biases in multi-class classifiers, tailored for high-risk NLP applications, surpassing traditional methods in both bias mitigation and prediction accuracy. Then, an analysis of the Bios dataset reveals the impact of dataset size on discriminatory biases and the limitations of standard fairness metrics. This awareness has led to explorations in the field of explainable AI, aiming for a more complete understanding of biases where traditional metrics are limited. Consequently, the thesis presents COCKATIEL, a model-agnostic explainability method that identifies and ranks concepts in Transformer models, outperforming previous approaches in sentiment analysis tasks. Finally, the thesis contributes to bridging the gap between fairness and explainability by introducing TaCo, a novel method to neutralize bias in Transformer model embeddings. In conclusion, this thesis constitutes a significant interdisciplinary endeavor that intertwines explicability and fairness to challenge and reshape current NLP paradigms. The methodologies and critiques presented contribute to the ongoing discourse on fairness in machine learning, offering actionable solutions for more equitable and responsible AI systems.
arXiv.org Artificial Intelligence
Oct-16-2024
- Country:
- North America
- United States
- Oregon > Multnomah County
- Portland (0.04)
- New York
- New York County > New York City (0.04)
- Monroe County > Rochester (0.04)
- Illinois > Champaign County
- Urbana (0.04)
- Oregon > Multnomah County
- Canada > Quebec
- Montreal (0.04)
- United States
- Europe
- Germany > Berlin (0.04)
- Austria > Vienna (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Bristol (0.04)
- France
- Provence-Alpes-Côte d'Azur (0.04)
- Occitanie > Haute-Garonne
- Toulouse (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America
- Genre:
- Overview (1.00)
- Research Report
- Promising Solution (1.00)
- New Finding (1.00)
- Experimental Study (1.00)
- Industry:
- Leisure & Entertainment (1.00)
- Information Technology > Security & Privacy (1.00)
- Health & Medicine (1.00)
- Government > Regional Government (0.92)
- Law > Civil Rights & Constitutional Law (0.92)
- Banking & Finance (0.92)
- Media (0.68)
- Energy (0.67)
- Technology:
- Information Technology > Artificial Intelligence
- Issues > Social & Ethical Issues (1.00)
- Natural Language
- Text Processing (1.00)
- Explanation & Argumentation (1.00)
- Machine Learning
- Statistical Learning (1.00)
- Performance Analysis > Accuracy (1.00)
- Neural Networks > Deep Learning (1.00)
- Learning Graphical Models > Directed Networks
- Bayesian Learning (0.46)
- Information Technology > Artificial Intelligence