Multi-Dimensional Gender Bias Classification

Dinan, Emily; Fan, Angela; Wu, Ledell; Weston, Jason; Williams, Adina

doi:10.18653/v1/2020.emnlp-main.23

Cited by 54 publications

(59 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al also proposes two methods for debiasing, one of which we also employ (i.e., CDA), and the other of which extends to sentences a word-embedding post-processing method (Bolukbasi et al, 2016) that has been shown to be ineffective at removing gender bias (Gonen and Goldberg 2019, but see for a more recent, perhaps more effective attempt). Finally-and as a direct extension of this work- Dinan et al (2020) decomposes gender bias along three semantic-pragmatic dimensions, and show that train more fine-grained classifiers allow for more accurate classification of dataset gender biases. The novelty of the present contribution lies in how we measure bias, and in the joint application of our three gender debiasing methods.…”

Section: Related Workmentioning

confidence: 80%

See 1 more Smart Citation

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Dinan

Fan

Williams

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

104

View full text Add to dashboard Cite

Social biases present in data are often directly reflected in the predictions of models trained on that data. We analyze gender bias in dialogue data, and examine how this bias is not only replicated, but is also amplified in subsequent generative chit-chat dialogue models. We measure gender bias in six existing dialogue datasets before selecting the most biased one, the multi-player textbased fantasy adventure dataset LIGHT (Urbanek et al., 2019), as a testbed for bias mitigation techniques. We consider three techniques to mitigate gender bias: counterfactual data augmentation, targeted data collection, and bias controlled training. We show that our proposed techniques mitigate gender bias by balancing the genderedness of generated dialogue utterances, and find that they are particularly effective in combination. We evaluate model performance with a variety of quantitative methods-including the quantity of gendered words, a dialogue safety classifier, and human assessments-all of which show that our models generate less gendered, but equally engaging chit-chat responses.

show abstract

Section: Related Workmentioning

confidence: 80%

“…Nouns and adjectives are binned into gendered bins via an aggregation of existing gendered word lists (Zhao et al, 2018b,a;Hoyle et al, 2019). Note that other functions could be used as well, such as a bias classifier (Dinan et al, 2020).…”

Section: Bias Controlled Trainingmentioning

confidence: 99%

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Dinan

Fan

Williams

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

104

View full text Add to dashboard Cite

show abstract

“…Bias metrics can also be categorized by how they define associations between demographic group attributes and text. Biases can be towards people described in text, people who produce the text, or people to whom the text is addressed (Dinan et al, 2020b). Most existing works define bias metrics through the first association-these biases are relatively easier to analyze, since both the demographic and the textual signals of bias are encapsulated within the text.…”

Section: Bias Definitions and Metricsmentioning

confidence: 99%

Societal Biases in Language Generation: Progress and Challenges

Sheng

Chang

Natarajan

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner. While techniques can effectively generate fluent text, they can also produce undesirable societal biases that can have a disproportionately negative impact on marginalized populations. Language generation presents unique challenges for biases in terms of direct user interaction and the structure of decoding techniques. To better understand these challenges, we present a survey on societal biases in language generation, focusing on how data and techniques contribute to biases and progress towards reducing biases. Motivated by a lack of studies on biases from decoding techniques, we also conduct experiments to quantify the effects of these techniques. By further discussing general trends and open challenges, we call to attention promising directions for research and the importance of fairness and inclusivity considerations for language generation applications.

show abstract

“…They applied logit pairing to improve CTF and assured robust accuracy for similar sentences targeting different demographics. In another work, Dinan et al (2020) decomposed gender bias in text along several pragmatic and semantic dimensions and proposed classifiers for controlling gender bias.…”

Section: Bias In System Outputmentioning

confidence: 99%

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Kiritchenko

Nejadgholi

Fraser

2021

jair

View full text Add to dashboard Cite

The pervasiveness of abusive content on the internet can lead to severe psychological and physical harm. Significant effort in Natural Language Processing (NLP) research has been devoted to addressing this problem through abusive content detection and related sub-areas, such as the detection of hate speech, toxicity, cyberbullying, etc. Although current technologies achieve high classification performance in research studies, it has been observed that the real-life application of this technology can cause unintended harms, such as the silencing of under-represented groups. We review a large body of NLP research on automatic abuse detection with a new focus on ethical challenges, organized around eight established ethical principles: privacy, accountability, safety and security, transparency and explainability, fairness and non-discrimination, human control of technology, professional responsibility, and promotion of human values. In many cases, these principles relate not only to situational ethical codes, which may be context-dependent, but are in fact connected to universal human rights, such as the right to privacy, freedom from discrimination, and freedom of expression. We highlight the need to examine the broad social impacts of this technology, and to bring ethical and human rights considerations to every stage of the application life-cycle, from task formulation and dataset design, to model training and evaluation, to application deployment. Guided by these principles, we identify several opportunities for rights-respecting, socio-technical solutions to detect and confront online abuse, including ‘nudging’, ‘quarantining’, value sensitive design, counter-narratives, style transfer, and AI-driven public education applications.evaluation, to application deployment. Guided by these principles, we identify several opportunities for rights-respecting, socio-technical solutions to detect and confront online abuse, including 'nudging', 'quarantining', value sensitive design, counter-narratives, style transfer, and AI-driven public education applications.

show abstract

Multi-Dimensional Gender Bias Classification

Cited by 54 publications

References 75 publications

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Societal Biases in Language Generation: Progress and Challenges

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Contact Info

Product

Resources

About