Seminars and Events
Bias and Power in NLP
Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom.
If you’re an outside visitor, please inform us at (nlg-seminar-host(at)isi.edu) beforehand so we’ll be aware of your attendance and let you in.
In-person attendance will be held in CR#689, remote attendees can log on via Zoom.
For more information on the NL Seminar series and upcoming talks, please visit:
NLP models are increasingly deployed as part of technological pipelines. However, these models reinforce the biased and unjust treatment of marginalized people. In this talk, I discuss the multiplicity & sociotechnical nature of “bias,” and sources of “bias” and harms in the NLP lifecycle, situating these concepts in the context of gender exclusivity. I further examine bias metrics, interventions, & their pitfalls. Finally, I connect “bias” and harms to the power structures in which NLP is embedded. Ultimately, I urge for more intersectional and reflexive approaches to NLP.
Arjun Subramonian is a Computer Science PhD student at the University of California, Los Angeles. Their research focuses on inclusive graph machine learning and natural language processing, including fairness, bias, ethics, and integrating queer perspectives. They are further a core organizer of Queer in AI.
The recording for this NL Seminar talk will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI.
Subscribe here to learn more about upcoming seminars: