Adhering, Steering, and Queering: Treatment of Gender in Natural Language Generation

By Yolande A. A. Strengers, Lizhen Qu, Qiongkai Xu, Jarrod Knibbe. 2020

49 citations recorded by the source corpus.

Natural Language Generation (NLG) supports the creation of personalized, contextualized, and targeted content. However, the algorithms underpinning NLG have come under scrutiny for reinforcing gender, racial, and other problematic biases. Recent research in NLG seeks to remove these biases through principles of fairness and privacy. Drawing on gender and queer theories from sociology and Science and Technology studies, we consider how NLG can contribute towards the advancement of gender equity in society. We propose a conceptual framework and technical parameters for aligning NLG with feminist HCI qualities. We present three approaches: (1) adhering to current approaches of removing sensitive gender attributes, (2) steering gender differences away from the norm, and (3) queering gender by troubling stereotypes. We discuss the advantages and limitations of these approaches across three hypothetical scenarios; newspaper headlines, job advertisements, and chatbots. We conclude by discussing considerations for implementing this framework and related ethical and equity agendas.

Subfields: Artificial Intelligence, Safety Research, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Aram Galstyan
2. Kai-Wei Chang
3. Richard S. Zemel
4. Rahul Gupta
5. Jwala Dhamala
6. Palash Goyal
7. Mohit Bansal
8. Ruslan Salakhutdinov

In Safety Research

1. Aram Galstyan
2. Richard S. Zemel
3. Kai-Wei Chang
4. Silvia Chiappa

In Human-Computer Interaction

1. Aram Galstyan
2. Kai-Wei Chang

Citations in the corpus

• Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020, neutral): “…Webster et al. (2019); Zmigrod et al. (2019); Gyamfi et al. (2020); Hube et al. (2020); Hutchinson et al. (2020); Kim et al. (2020); Nadeem et al. (2020); Papakyriakopoulos et al. (2020); Ravfogel et al. (2020); Rozado (2020); Sen and Ganguly (2020); Shin et al. (2020); Strengers et al. (2020).”
• “I’m fully who I am”: Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation (2023, background): “, [43, 60, 63]) have focused on understanding how LLM harms appear for the TGNB community.”