MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline

• URL: http://arxiv.org/abs/2006.11642v1
• Date: Sat, 20 Jun 2020 20:03:07 GMT
• Title: MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline
• Authors: Yuhao Du and Kenneth Joseph
• Abstract summary: Existing methods for debiasing word embeddings often do so only superficially, in that words that are stereotypically associated with a particular gender can still be clustered together in the debiased space. This paper explores why this residual clustering exists, and how it might be addressed. We identify two potential reasons for which residual bias exists and develop a new pipeline, MDR Cluster-Debias, to mitigate this bias.
• Score: 3.180013942295509
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing methods for debiasing word embeddings often do so only superficially, in that words that are stereotypically associated with, e.g., a particular gender in the original embedding space can still be clustered together in the debiased space. However, there has yet to be a study that explores why this residual clustering exists, and how it might be addressed. The present work fills this gap. We identify two potential reasons for which residual bias exists and develop a new pipeline, MDR Cluster-Debias, to mitigate this bias. We explore the strengths and weaknesses of our method, finding that it significantly outperforms other existing debiasing approaches on a variety of upstream bias tests but achieves limited improvement on decreasing gender bias in a downstream task. This indicates that word embeddings encode gender bias in still other ways, not necessarily captured by upstream tests.

Related papers

• Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns [53.62845317039185]
  Bias-measuring datasets play a critical role in detecting biased behavior of language models. We propose a novel method to collect diverse, natural, and minimally distant text pairs via counterfactual generation. We show that four pre-trained language models are significantly more inconsistent across different gender groups than within each group.
  arXiv  Detail & Related papers  (2023-02-11T12:11:03Z)
• Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference [20.112129592923246]
  We focus on an overlooked aspect of the overlap bias in NLI models: the reverse word-overlap bias. Current NLI models are highly biased towards the non-entailment label on instances with low overlap. We investigate the reasons for the emergence of the overlap bias and the role of minority examples in its mitigation.
  arXiv  Detail & Related papers  (2022-11-07T21:02:23Z)
• 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)
• Identifying and Mitigating Gender Bias in Hyperbolic Word Embeddings [34.378806636170616]
  We extend the study of gender bias to the recently popularized hyperbolic word embeddings. We propose gyrocosine bias, a novel measure for quantifying gender bias in hyperbolic word representations. Experiments on a suit of evaluation tests show that Poincar'e Gender Debias (PGD) effectively reduces bias while adding a minimal semantic offset.
  arXiv  Detail & Related papers  (2021-09-28T14:43:37Z)
• The Gap on GAP: Tackling the Problem of Differing Data Distributions in Bias-Measuring Datasets [58.53269361115974]
  Diagnostic datasets that can detect biased models are an important prerequisite for bias reduction within natural language processing. undesired patterns in the collected data can make such tests incorrect. We introduce a theoretically grounded method for weighting test samples to cope with such patterns in the test data.
  arXiv  Detail & Related papers  (2020-11-03T16:50:13Z)
• Robustness and Reliability of Gender Bias Assessment in Word Embeddings: The Role of Base Pairs [23.574442657224008]
  It has been shown that word embeddings can exhibit gender bias, and various methods have been proposed to quantify this. Previous work has leveraged gender word pairs to measure bias and extract biased analogies. We show that the reliance on these gendered pairs has strong limitations. In particular, the well-known analogy "man is to computer-programmer as woman is to homemaker" is due to word similarity rather than societal bias.
  arXiv  Detail & Related papers  (2020-10-06T16:09:05Z)
• Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation [57.292988892028134]
  Bolukbasi et al. present one of the first gender bias mitigation techniques for word representations. We generalize their method to a kernelized, nonlinear version. We analyze empirically whether the bias subspace is actually linear.
  arXiv  Detail & Related papers  (2020-09-20T14:13:45Z)
• Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings [37.65897382453336]
  Existing post-processing methods for debiasing word embeddings are unable to mitigate gender bias hidden in the spatial arrangement of word vectors. We propose RAN-Debias, a novel gender debiasing methodology which eliminates the bias present in a word vector but also alters the spatial distribution of its neighbouring vectors. We also propose a new bias evaluation metric - Gender-based Illicit Proximity Estimate (GIPE)
  arXiv  Detail & Related papers  (2020-06-02T20:50:43Z)
• Mitigating Gender Bias Amplification in Distribution by Posterior Regularization [75.3529537096899]
  We investigate the gender bias amplification issue from the distribution perspective. We propose a bias mitigation approach based on posterior regularization. Our study sheds the light on understanding the bias amplification.
  arXiv  Detail & Related papers  (2020-05-13T11:07:10Z)
• Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation [94.98656228690233]
  We propose a technique that purifies the word embeddings against corpus regularities prior to inferring and removing the gender subspace. Our approach preserves the distributional semantics of the pre-trained word embeddings while reducing gender bias to a significantly larger degree than prior approaches.
  arXiv  Detail & Related papers  (2020-05-03T02:33:20Z)

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.