Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias

• URL: http://arxiv.org/abs/2010.14534v1
• Date: Tue, 27 Oct 2020 18:06:09 GMT
• Title: Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
• Authors: Marion Bartl and Malvina Nissim and Albert Gatt
• Abstract summary: Contextualized word embeddings have been replacing standard embeddings in NLP systems. We measure gender bias by studying associations between gender-denoting target words and names of professions in English and German. We show that our method of measuring bias is appropriate for languages with a rich and gender-marking, such as German.
• Score: 12.4543414590979
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to assess biases encoded in their replacements as well. Focusing on BERT (Devlin et al., 2018), we measure gender bias by studying associations between gender-denoting target words and names of professions in English and German, comparing the findings with real-world workforce statistics. We mitigate bias by fine-tuning BERT on the GAP corpus (Webster et al., 2018), after applying Counterfactual Data Substitution (CDS) (Maudslay et al., 2019). We show that our method of measuring bias is appropriate for languages such as English, but not for languages with a rich morphology and gender-marking, such as German. Our results highlight the importance of investigating bias and mitigation techniques cross-linguistically, especially in view of the current emphasis on large-scale, multilingual language models.

Related papers

• The Lou Dataset -- Exploring the Impact of Gender-Fair Language in German Text Classification [57.06913662622832]
  Gender-fair language fosters inclusion by addressing all genders or using neutral forms. Gender-fair language substantially impacts predictions by flipping labels, reducing certainty, and altering attention patterns. While we offer initial insights on the effect on German text classification, the findings likely apply to other languages.
  arXiv  Detail & Related papers  (2024-09-26T15:08:17Z)
• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• What is Your Favorite Gender, MLM? Gender Bias Evaluation in Multilingual Masked Language Models [8.618945530676614]
  This paper proposes an approach to estimate gender bias in multilingual lexicons from 5 languages: Chinese, English, German, Portuguese, and Spanish. A novel model-based method is presented to generate sentence pairs for a more robust analysis of gender bias. Our results suggest that gender bias should be studied on a large dataset using multiple evaluation metrics for best practice.
  arXiv  Detail & Related papers  (2024-04-09T21:12:08Z)
• Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation [28.471506840241602]
  Gender bias is a significant issue in machine translation, leading to ongoing research efforts in developing bias mitigation techniques. We propose a bias mitigation method based on a novel approach. Gender-Aware Contrastive Learning, GACL, encodes contextual gender information into the representations of non-explicit gender words.
  arXiv  Detail & Related papers  (2023-05-23T12:53:39Z)
• Language-Agnostic Bias Detection in Language Models with Bias Probing [22.695872707061078]
  Pretrained language models (PLMs) are key components in NLP, but they contain strong social biases. We propose a bias probing technique called LABDet for evaluating social bias in PLMs with a robust and language-agnostic method. We find consistent patterns of nationality bias across monolingual PLMs in six languages that align with historical and political context.
  arXiv  Detail & Related papers  (2023-05-22T17:58:01Z)
• Efficient Gender Debiasing of Pre-trained Indic Language Models [0.0]
  The gender bias present in the data on which language models are pre-trained gets reflected in the systems that use these models. In our paper, we measure gender bias associated with occupations in Hindi language models. Our results reflect that the bias is reduced post-introduction of our proposed mitigation techniques.
  arXiv  Detail & Related papers  (2022-09-08T09:15:58Z)
• Evaluating Gender Bias in Hindi-English Machine Translation [0.1503974529275767]
  We implement a modified version of the TGBI metric based on the grammatical considerations for Hindi. We compare and contrast the resulting bias measurements across multiple metrics for pre-trained embeddings and the ones learned by our machine translation model.
  arXiv  Detail & Related papers  (2021-06-16T10:35:51Z)
• Decoding and Diversity in Machine Translation [90.33636694717954]
  We characterize differences between cost diversity paid for the BLEU scores enjoyed by NMT. Our study implicates search as a salient source of known bias when translating gender pronouns.
  arXiv  Detail & Related papers  (2020-11-26T21:09:38Z)
• Gender Stereotype Reinforcement: Measuring the Gender Bias Conveyed by Ranking Algorithms [68.85295025020942]
  We propose the Gender Stereotype Reinforcement (GSR) measure, which quantifies the tendency of a Search Engines to support gender stereotypes. GSR is the first specifically tailored measure for Information Retrieval, capable of quantifying representational harms.
  arXiv  Detail & Related papers  (2020-09-02T20:45:04Z)
• Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer [101.58431011820755]
  We study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations.
  arXiv  Detail & Related papers  (2020-05-02T04:34:37Z)
• 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.