Home
Blog
Contact
Contact
Contact
Contact
柯玫瑰
Hannah Rose Kirk
I’m Hannah Rose Kirk.

keywords = {
Data-centric AI
;
Online Safety
;
Bias Mitigation
;
Statistics
;
China AI
;
Data-centric AI
;
Oxford Internet Institute
;
The Alan Turing Institute
;
Oxford AI Society
;
Cambridge University
;
Peking University
;
Oxford Internet Institute
;
Sci-Fi Books
;
Sushi
;
Documentaries
;
Learning Mandarin
;
Cycling
;
Sci-Fi Books
;
}
LEARN MORE

print MySummary

I am an AI Researcher at
the University of Oxford and The Alan Turing Institute.

My current research centres on the application of machine learning, natural language processing and computer vision techniques for the detection of varied forms of online harms, such as hate speech and societal biases.

Whilst living in Beijing for two years, I focused on the governance of emerging technologies, data privacy legislation, intercultural digital ethics and China’s AI strategy.

Education

.class GetDegrees

2021 - 2024

Oxford Internet Institute, University of Oxford

DPhil in Social Data Science
Fully-funded scholarship
2020 - 2021

Oxford Internet Institute, University of Oxford

MSc in Social Data Science
Distinction, 77%
Awarded the Oxford Internet Institute Thesis Prize for best graduate dissertation
2018-2020

Yenching Academy, Peking University

MA in China Studies and Economics
GPA: 3.99, Rank: 2/99
2015 - 2018

Trinity College, University of Cambridge

BA in Economics
Double First Class Honours
Awarded the Roger Dennis Prize for best undergraduate dissertation

Professional Experience

.class AddExperience

Sept 2021 - Present

The Alan Turing Institute

NLP Researcher
Monitoring and detecting harmful language
Sept 2021 - Present

Rewire Online

ML Engineer
Implementing NLP solutions for online safety
Oct 2020 - Present

Oxford Artificial Intelligence Society

Research Project Manager
Leading student research projects on AI bias
Sept 2019 - Sept 2020

The Berggruen Institute, China Center

Researcher
Linking Chinese philosophy to AI and privacy

Skills

.class BuildSkills

Languages

English
Native
Mandarin
Intermediate

Skills

  • Python
  • PyTorch
  • Tensorflow
  • R

Domains

  • Online harms
  • Bias in NLP
  • Active Learning
  • China AI

Publications

return Output

05
/
23
/
22

Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements

Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (NAACL 2022)
Conrad Borchers, Dalia Sara Gala, Benjamin Gilburt, Eduard Oravkin, Wilfried Bounsi, Yuki M. Asano, Hannah Rose Kirk
04
/
29
/
22

Handling and Presenting Harmful Text

arXiv
Hannah Rose Kirk, Abeba Birhane, Bertie Vidgen, Leon Derczynski
03
/
22
/
22

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning

arXiv
Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat, Wonsuk Yang, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain
12
/
01
/
21

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models

NeurIPS 2021
Hannah Rose Kirk, Yennie Jun, Haider Iqbal, Elias Benussi, Filippo Volpin, Frederic A. Dreyer, Aleksandar Shtedritski & Yuki M. Asano
09
/
01
/
21

Hatemoji: A test suite and adversarially-generated dataset for benchmarking and detecting emoji-based hate

NAACL 2022
Hannah Rose Kirk, Bertram Vidgen, Paul Röttger, Tristan Thrush & Scott A. Hale
08
/
01
/
21

Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset

Proceedings of the 5th Workshop on Online Abuse and Harms (ACL 2021)
Hannah Rose Kirk, Yennie Jun, Paulius Rauba, Gal Wachtel, Ruining Li, Xingjian Bai, Noah Broestl, Martin Doff-Sotta, Aleksandar Shtedritski, & Yuki M Asano
08
/
19
/
20

The Nuances of Confucianism in Technology Policy: an Inquiry into the Interaction Between Cultural and Political Systems in Chinese Digital Ethics

International Journal of Politics, Culture, and Society
Hannah Rose Kirk, Kangkyu Lee & Carlisle Micallef

Upcoming Events + Talks

.class FindEvents