Toward Understanding Bias Correlations for Mitigation in NLP

• URL: http://arxiv.org/abs/2205.12391v1
• Date: Tue, 24 May 2022 22:48:47 GMT
• Title: Toward Understanding Bias Correlations for Mitigation in NLP
• Authors: Lu Cheng, Suyu Ge, Huan Liu
• Abstract summary: This work aims to provide a first systematic study toward understanding bias correlations in mitigation. We examine bias mitigation in two common NLP tasks -- toxicity detection and word embeddings. Our findings suggest that biases are correlated and present scenarios in which independent debiasing approaches may be insufficient.
• Score: 34.956581421295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have responded with unprecedented effort and proposed promising approaches for bias mitigation. In spite of considerable practical importance, current algorithmic fairness literature lacks an in-depth understanding of the relations between different forms of biases. Social bias is complex by nature. Numerous studies in social psychology identify the "generalized prejudice", i.e., generalized devaluing sentiments across different groups. For example, people who devalue ethnic minorities are also likely to devalue women and gays. Therefore, this work aims to provide a first systematic study toward understanding bias correlations in mitigation. In particular, we examine bias mitigation in two common NLP tasks -- toxicity detection and word embeddings -- on three social identities, i.e., race, gender, and religion. Our findings suggest that biases are correlated and present scenarios in which independent debiasing approaches dominant in current literature may be insufficient. We further investigate whether jointly mitigating correlated biases is more desired than independent and individual debiasing. Lastly, we shed light on the inherent issue of debiasing-accuracy trade-off in bias mitigation. This study serves to motivate future research on joint bias mitigation that accounts for correlated biases.

Related papers

• Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP [64.45845091719002]
  Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. This paper seeks to clarify the current situation and plot a course for meaningful progress in fair learning.
  arXiv  Detail & Related papers  (2023-02-11T14:54:00Z)
• Causal foundations of bias, disparity and fairness [0.0]
  We propose to define bias as a direct causal effect that is unjustified. We propose to define disparity as a direct or indirect causal effect that includes a bias. Our proposed definitions can be used to study biases and disparities in a more rigorous and systematic way.
  arXiv  Detail & Related papers  (2022-07-27T17:33:04Z)
• The SAME score: Improved cosine based bias score for word embeddings [49.75878234192369]
  We introduce SAME, a novel bias score for semantic bias in embeddings. We show that SAME is capable of measuring semantic bias and identify potential causes for social bias in downstream tasks.
  arXiv  Detail & Related papers  (2022-03-28T09:28:13Z)
• A Survey on Bias and Fairness in Natural Language Processing [1.713291434132985]
  We analyze the origins of biases, the definitions of fairness, and how different subfields of NLP bias can be mitigated. We discuss how future studies can work towards eradicating pernicious biases from NLP algorithms.
  arXiv  Detail & Related papers  (2022-03-06T18:12:30Z)
• Anatomizing Bias in Facial Analysis [86.79402670904338]
  Existing facial analysis systems have been shown to yield biased results against certain demographic subgroups. It has become imperative to ensure that these systems do not discriminate based on gender, identity, or skin tone of individuals. This has led to research in the identification and mitigation of bias in AI systems.
  arXiv  Detail & Related papers  (2021-12-13T09:51:13Z)
• Statistical discrimination in learning agents [64.78141757063142]
  Statistical discrimination emerges in agent policies as a function of both the bias in the training population and of agent architecture. We show that less discrimination emerges with agents that use recurrent neural networks, and when their training environment has less bias.
  arXiv  Detail & Related papers  (2021-10-21T18:28:57Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)
• Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases [10.713568409205077]
  State-of-the-art neural language models generate dynamic word embeddings dependent on the context in which the word appears. We introduce the Contextualized Embedding Association Test (CEAT), that can summarize the magnitude of overall bias in neural language models. We develop two methods, Intersectional Bias Detection (IBD) and Emergent Intersectional Bias Detection (EIBD), to automatically identify the intersectional biases and emergent intersectional biases from static word embeddings.
  arXiv  Detail & Related papers  (2020-06-06T19:49:50Z)
• Towards Controllable Biases in Language Generation [87.89632038677912]
  We develop a method to induce societal biases in generated text when input prompts contain mentions of specific demographic groups. We analyze two scenarios: 1) inducing negative biases for one demographic and positive biases for another demographic, and 2) equalizing biases between demographics.
  arXiv  Detail & Related papers  (2020-05-01T08:25:11Z)
• Interventions for Ranking in the Presence of Implicit Bias [34.23230188778088]
  Implicit bias is the unconscious attribution of particular qualities (or lack thereof) to a member from a particular social group. Rooney Rule is a constraint to improve the utility of the outcome for certain cases of the subset selection problem. We present a family of simple and interpretable constraints and show that they can optimally mitigate implicit bias.
  arXiv  Detail & Related papers  (2020-01-23T19:11:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.