Bio

Yi-Ling is a Research Associate in the Online Safety Team within the public policy programme, working on applying machine learning and natural language processing methods to tackle online harm. Her research has mainly focused on toxicity mitigation via data curation and counter speech generation, with an emphasis on multilinguality and informativeness. She obtained her PhD degree (Cum Laude) in Information and Communication Technologies at the University of Trento.

Research interests

Her work centres around social implications of NLP, such as understanding the dynamics of hate speech and counter speech that can provide insights on best countermeasures for online toxicity.