Gender Bias in Coreference Resolution

Rudinger, Rachel; Naradowsky, Jason; Leonard, Brian; Durme, Benjamin Van

doi:10.18653/v1/n18-2002

Cited by 324 publications

(373 citation statements)

References 18 publications

Supporting

Mentioning

338

Contrasting

Order By: Relevance

“…The results prove that BERT expresses strong preferences for male pronouns, raising concerns with using BERT in downstream tasks like resume filtering. Table 5: Percentage of attributes associated more strongly with the male gender 6 Related Work NLP applications ranging from core tasks such as coreference resolution (Rudinger et al, 2018) and language identification (Jurgens et al, 2017), to downstream systems such as automated essay scoring (Amorim et al, 2018), exhibit inherent social biases which are attributed to the datasets used to train the embeddings (Barocas and Selbst, 2016;Zhao et al, 2017;Yao and Huang, 2017).…”

Section: Real World Implicationsmentioning

confidence: 99%

Measuring Bias in Contextualized Word Representations

Kurita¹,

Vyas²,

Pareek³

et al. 2019

Proceedings of the First Workshop on Gender Bias in Natural Language Processing

280

275

View full text Add to dashboard Cite

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1) propose a template-based method to quantify bias in BERT;(2) show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3) conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case study focuses on gender bias, the proposed technique is generalizable to unveiling other biases, including in multiclass settings, such as racial and religious biases.

show abstract

Section: Real World Implicationsmentioning

confidence: 99%

Measuring Bias in Contextualized Word Representations

Kurita¹,

Vyas²,

Pareek³

et al. 2019

Proceedings of the First Workshop on Gender Bias in Natural Language Processing

280

275

View full text Add to dashboard Cite

show abstract

“…For coreference resolution, Rudinger et al (2018) and Zhao et al (2018b) independently designed GBETs based on Winograd Schemas. The corpus consists of sentences which contain a gender-neutral occupation (e.g., doctor), a secondary participant (e.g., patient), and a gendered pronoun that refers either the occupation or the participant.…”

Section: Taskmentioning

confidence: 99%

“…If that same model predicts females and males coreferent to "doctor" with 20% and 60% accuracy, respectively, then the global average accuracy for each gender is equivalent, yet the model exhibits bias. 1 Therefore, Zhao et al (2018b) and Rudinger et al (2018) design metrics to analyze gender bias by examining how the performance difference between genders with respect to each occupation correlate with the occupational gender statistics from the U.S Bureau of Labor Statistics.…”

Section: Taskmentioning

confidence: 99%

Mitigating Gender Bias in Natural Language Processing: Literature Review

Sun¹,

Gaut²,

Tang³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

317

228

View full text Add to dashboard Cite

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in modeling various applications, they propagate and may even amplify gender bias found in text corpora. While the study of bias in artificial intelligence is not new, methods to mitigate gender bias in NLP are relatively nascent. In this paper, we review contemporary studies on recognizing and mitigating gender bias in NLP. We discuss gender bias based on four forms of representation bias and analyze methods recognizing gender bias. Furthermore, we discuss the advantages and drawbacks of existing gender debiasing methods. Finally, we discuss future studies for recognizing and mitigating gender bias in NLP.

show abstract

“…This results in gender-stereotypical vector analogiesà la Mikolov et al (2013), such as man:computer programmer :: woman:homemaker (Bolukbasi et al, 2016), and such bias has been shown to materialise in a variety of downstream tasks, e.g. coreference resolution (Rudinger et al, 2018;Zhao et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution

Maudslay¹,

Gonen²,

Cotterell³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA), in which a corpus is duplicated and augmented to remove bias, e.g. by swapping all inherently-gendered words in the copy. We perform an empirical comparison of these approaches on the English Gigaword and Wikipedia, and find that whilst both successfully reduce direct bias and perform well in tasks which quantify embedding quality, CDA variants outperform projection-based methods at the task of drawing non-biased gender analogies by an average of 19% across both corpora. We propose two improvements to CDA: Counterfactual Data Substitution (CDS), a variant of CDA in which potentially biased text is randomly substituted to avoid duplication, and the Names Intervention, a novel name-pairing technique that vastly increases the number of words being treated. CDA/S with the Names Intervention is the only approach which is able to mitigate indirect gender bias: following debiasing, previously biased words are significantly less clustered according to gender (cluster purity is reduced by 49%), thus improving on the state-of-the-art for bias mitigation.

show abstract

Gender Bias in Coreference Resolution

Cited by 324 publications

References 18 publications

Measuring Bias in Contextualized Word Representations

Measuring Bias in Contextualized Word Representations

Mitigating Gender Bias in Natural Language Processing: Literature Review

It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution

Contact Info

Product

Resources

About