Robustness and Reliability of Gender Bias Assessment in Word Embeddings: The Role of Base Pairs

• URL: http://arxiv.org/abs/2010.02847v2
• Date: Tue, 27 Oct 2020 21:24:16 GMT
• Title: Robustness and Reliability of Gender Bias Assessment in Word Embeddings: The Role of Base Pairs
• Authors: Haiyang Zhang, Alison Sneyd and Mark Stevenson
• Abstract summary: 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.
• Score: 23.574442657224008
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It has been shown that word embeddings can exhibit gender bias, and various methods have been proposed to quantify this. However, the extent to which the methods are capturing social stereotypes inherited from the data has been debated. Bias is a complex concept and there exist multiple ways to define it. 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: bias measures based off of them are not robust and cannot identify common types of real-world bias, whilst analogies utilising them are unsuitable indicators of bias. 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. This has important implications for work on measuring bias in embeddings and related work debiasing embeddings.

Related papers

• ''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Text [11.085070600065801]
  Language serves as a powerful tool for the manifestation of societal belief systems. Gender bias is one of the most pervasive biases in our society. We create the first dataset of GPT-generated English text with normative ratings of gender bias.
  arXiv  Detail & Related papers  (2023-10-26T14:34:06Z)
• DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Bias [13.928591341824248]
  Debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its predictions. This evaluation protocol overlooks the possible adverse impact of bias mitigation on useful gender knowledge.
  arXiv  Detail & Related papers  (2023-10-22T15:27:16Z)
• The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated [70.23064111640132]
  We compare the impact of debiasing on performance across multiple downstream tasks using a wide-range of benchmark datasets. Experiments show that the effects of debiasing are consistently emphunderestimated across all tasks.
  arXiv  Detail & Related papers  (2023-09-16T20:25:34Z)
• Gender Biases in Automatic Evaluation Metrics for Image Captioning [87.15170977240643]
  We conduct a systematic study of gender biases in model-based evaluation metrics for image captioning tasks. We demonstrate the negative consequences of using these biased metrics, including the inability to differentiate between biased and unbiased generations. We present a simple and effective way to mitigate the metric bias without hurting the correlations with human judgments.
  arXiv  Detail & Related papers  (2023-05-24T04:27:40Z)
• 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)
• Evaluating Metrics for Bias in Word Embeddings [64.55554083622258]
  We formalize a bias definition based on the ideas from previous works and derive conditions for bias metrics. We propose a new metric, SAME, to address the shortcomings of existing metrics and mathematically prove that SAME behaves appropriately.
  arXiv  Detail & Related papers  (2021-11-15T16:07:15Z)
• 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)
• Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models [5.378664454650768]
  This paper proposes two intuitive metrics, skew and stereotype, that quantify and analyse the gender bias present in contextual language models. We find evidence that gender stereotype correlates approximately negatively with gender skew in out-of-the-box models, suggesting that there is a trade-off between these two forms of bias.
  arXiv  Detail & Related papers  (2021-01-24T10:57:59Z)
• MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline [3.180013942295509]
  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.
  arXiv  Detail & Related papers  (2020-06-20T20:03:07Z)
• 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)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

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.