Sandro Pezzelle

Sandro Pezzelle

Assistant Professor

Sandro Pezzelle is an Assistant Professor in Responsible AI at the ILLC, University of Amsterdam. His research stems from an overarching question key to developing reliable and interpretable language technology: Can AI systems genuinely understand human language? Using insights from linguistics and cognitive science, he uses deep-learning NLP models (such as LLMs) to study semantics, that is, the meaning of words, phrases, and sentences. Before becoming a faculty member, he worked as a postdoc at the ILLC and obtained his PhD at CIMeC, University of Trento. He is a member of ACL and the ELLIS society.

Responsible White
Language models White
Explainable White
Inclusive White

Research projects of the researcher

Below you can find a sample of the CERTAIN-related research projects of this researcher.

Inclusive Image and Video Captioning

Current AI systems describing the content of images and videos in natural language often make assumptions about the gender, nationality, or physical appearance of the people in them. In this project, we aim to fix this unwanted behavior by developing more inclusive systems.
Bias White
Inclusive White

Papers by the researcher

Dealing with semantic underspecification in multimodal NLP