Debora Nozza (she/her) is an Assistant Professor in Computing Sciences at Bocconi University. She was awarded a €1.5m ERC Starting Grant project 2023 for research on personalized and subjective approaches to Natural Language Processing. Previously, she was awarded a €120,000 grant from Fondazione Cariplo for her project MONICA, which focuses on monitoring coverage, attitudes, and accessibility of Italian measures in response to COVID-19. Her research interests mainly focus on Natural Language Processing, specifically on the detection and counter-acting of hate speech and algorithmic bias on Social Media data in multilingual context. She is also deeply interested in understanding how and why people use large language models (LLMs) in their everyday lives.
She is an organizer of the Workshop on Online Abuse and Harms (WOAH) and Workshop on Gender Bias in Natural Language Processing (GeBNLP) at *ACL conferences. She was among the organizers of several shared tasks, including the first Homotransphobia Detection in Italian (HODI) at Evalita 2023, Automatic Misogyny Identification (AMI) at Evalita 2018 and Evalita 2020, as well as HatEval Task 5 at SemEval 2019, which focused on multilingual detection of hate speech against immigrants and women in Twitter.
PhD in Computer Science, 2018
University of Milano Bicocca
[29/09/24] Keynote Talk about Unmasking and Tackling Bias in Vision-Language Models at ECCV for the 1st workshop on critical evaluation of generative models and their impact on society
[01/09/24] My ERC Starting Grant project [PERSONAE)(https://www.deboranozza.com/project/personae/) has started!
[15/08/24] Keynote Talk at WASSA Workshop, ACL 2024.
[15/08/24] Panelist at HuCLLM - Human-Centered Large Language Modeling Workshop, ACL 2024.
[01/12/23] New paper on A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation published at EMNLP 2023.