News

[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](https://sites.google.com/view/cegis-workshop/home)

[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.

[06/09/23] I’m thrilled and honored to have been awarded a €1.5m ERC Starting Grant project 2023 for my project PERSONAE.

[05/09/23] Organizer of HODI, the first shared task on Homotransphobia Detection in Italian at 8th evaluation campaign EVALITA 2023.

[05/09/23] Organizer of EMit at EVALITA 2023: the Categorical Emotion Detection in Italian Social Media Task.

[19/07/23] Come work with me! New position open for a postdoc starting this year. See the call here

[13/07/23] Organizer of the 7th Workshop on Online Abuse and Harms (WOAH) at ACL 2023.

[13/07/23] New paper on Respectful or Toxic? Using Zero-Shot Learning with Language Models to Detect Hate Speech published at WOAH workshop at ACL 2023.

[13/07/23] New paper on What about ‘’em’’? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns published at ACL 2023.

[13/07/23] New paper on The State of Profanity Obfuscation in Natural Language Processing Scientific Publications published at Findings of ACL 2023.

[13/07/23] New paper on A Multi-dimensional study on Bias in Vision-Language models published at Findings of ACL 2023.

[05/07/23] Invited Talk about Fairness of Generative AI for the Italian Publishers Association (AIE).

[18/06/23] My first editorial piece has been published on Sole 24 ore! You can read it here.

[07/06/23] New paper on Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale published at FAACT 2023.

[05/06/23] Organizer of the ICWSM 2023 Data Challenge: Temporal social data at ICWSM 2023.

[10/05/23] Webinar Talk for A+I Algoritmi+Inclusivi about the positive impact of AI.

[09/05/23] Invited Talk at #ScienzaEspresso at #casaXiaomi in Milan about Fairness of Generative AI.

[07/05/23] New paper on A Cross-Lingual Study of Homotransphobia on Twitter published at C3NLP workshop at EACL 2023.

[07/05/23] New paper on ferret: a Framework for Benchmarking Explainers on Transformers published at EACL 2023: System Demonstration.

[27/04/23] Workshop Speaker at the NCRM/Exeter Computational Communication Methods Spring School.

[14/03/23] Invited Talk at University of Edinburgh.

[15/12/22] Invited Talk at GESIS Leibniz Institute for the Social Sciences.

[30/11/22] Organizer of the 6th Workshop on Natural Language for Artificial Intelligence (NL4AI).

[07/10/22] Invited Talk at INRIA Paris.

[04/10/22] Invited Talk at Fondazione Bruno Kessler in Trento.

[01/09/22] Officially started as Assistant Professor in Computing Sciences at Bocconi University.

[19/07/22] Seminar presentation on the Roadmap to Universal Hate Speech Detection at the Digital Democracies Institute at Simon Fraser University.

[18/07/22] Seminar presentation on the Roadmap to Universal Hate Speech Detection at the University of British Columbia.

[12/07/22] My #betterposter at NAACL 2022.

[12/07/22] New paper on HATE-ITA: Hate Speech Detection in Italian Social Media Text published at WOAH workshop at NAACL 2022.

[12/07/22] New paper on Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models published at WOAH workshop at NAACL 2022.

[27/06/22] Invited speaker at Fairness in Artificial Intelligence workshop organized by Bocconi University in partnership with Associazione EDGE.

[02/03/22] 5 paper on hate speech detection, bias, and multilinguality published at ACL workshops.

[01/03/22] New paper on Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists published at ACL findings.

[06/08/21] My first single-authored paper on Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection published at ACL.