Raffaella Bernardi
Raffaella Bernardi earned a doctorate at Utrecht in June 2002 with a dissertation on categorial type logic. She worked at the Free University of Bozen-Bolzano from 2002 to 2010, developing natural language interfaces to structured data. In 2011 she began work on distributional semantics, its compositional properties, and its integration with computer vision models. Her research focuses on multimodal models in interactive settings, including visual dialogue. Her work connects logic and computational semantics with language technology and learning from several kinds of input.
Timeline
-
1999–2002
Logic and language
Bernardi joined Utrecht’s international doctoral programme in 1999. She defended a dissertation on categorial type logic in June 2002. She studied logic and language at Utrecht and Amsterdam, forming the basis of her work on meaning.
-
2002–2010
Natural language and structured data
She worked at the Free University of Bozen-Bolzano from 2002 to 2010. Her research took a computational direction in October 2002, with natural language interfaces to structured data. She also taught computational linguistics and worked on question answering and controlled language interfaces.
-
2011
Distributional semantics and vision
She began work on distributional semantics in 2011. She investigated how meaning representations compose and how they can be combined with computer vision models. This connects her earlier formal language research with learned representations from language and visual data.
-
As of October 2026
Interactive multimodal models
Her focus is multimodal models in interactive settings, including visual dialogue. She also participates in the COMPOSES research team and teaches language technology.
Sources and credits
Photo: ellis.eu; creator not stated. License: Not stated by source. Source: ellis.eu. Cropped to a square and resized. Ask us to remove or replace this photo.