I am a second-year PhD student in Computer Science at the University of Washington. I am advised by Luke Zettlemoyer and work on various topics in NLP. Before UW, I was a master student at the Language and Technologies Institute (LTI) at CMU with Yulia Tsvetkov. In 2018, I worked at Microsoft AI Frameworks for a year. I studied physics, math, and computer science at Harvard where I obtained an AB/SM. I am Italian and German, and attended a French school in Rome for fifteen years.

Language and reasoning are intricately related – one is the means through which the other can exist and be expressed. A fascinating aspect about NLP research is that a deeper understanding of language can shed light on human hinking. What ultimately motivates me is the hope of going beyond pattern recognitionand finding linguistically grounded models of language capable of understanding, reasoning, and generating text as effectively and reliably as humans do.

In my research, I have developed a pretraining objective for improved controllability of summarization systems, investigated language models’ reasoning abilities, and their factual errors, as well as societal challenge associated with their use.

NLP is rapidly transitioning from research to a core element of modern applications. By devising computationally efficient NLP systems, I hope to improve the accessibility of NLP and its environmental impact. I previously worked on bringing machine learning tools to a wide audience of developers while at Microsoft where I worked on an open-source machine learning library ML.NET.


I love sports. I was on the CMU fencing club. Previously, I was part of the Harvard Fencing varsity team, and competed internationally in modern pentathlon back in Italy.