Gabriele Sarti

MSc Data Science

University of Trieste & SISSA


Hey there! I have recently graduated from the Data Science MSc program at the University of Trieste and SISSA. For my thesis project, I worked with the ItaliaNLP Lab and the L2R Lab under the joint supervision of Felice Dell’Orletta and Davide Crepaldi on NLP and psycholinguistics perspectives for linguistic complexity assessment.

My research interests focus on interpreting deep models and understanding their learning dynamics, in particular when dealing with natural language. I am also interested in positive social applications of machine learning and ethical AI.


  • Natural Language Understanding
  • Interpretability in Deep Learning
  • Representation Learning
  • Psycholinguistics


  • MSc in Data Science, 2020

    University of Trieste & SISSA, IT

  • DEC in Software Management, 2018

    Cégep de Saint-Hyacinthe, CA



  • My master’s thesis “Interpreting Neural Language Models for Linguistic Complexity Assessment” is available in PDF/Gitbook formats here. Feedback and comments are welcome! 🙂

  • 18/12/2020: My system UmBERTo-MTSA received a special mention at the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA 2020).

  • 11/12/2020: Graduated from the Data Science MSc: 110 Cum Laude! 🎉

Selected Publications

Interpreting Neural Language Models for Linguistic Complexity Assessment

This thesis presents a model-driven study of multiple phenomena associated with linguistic complexity, and how those get encoded by …

Italian Transformers Under the Linguistic Lens

We investigate whether and how using different architectures of probing models affects the performance of Italian transformers in …

[email protected] AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations

This work describes a self-supervised data augmentation approach used to improve learning models' performances when only a moderate …

Blog posts

ICLR 2020 Trends: Better & Faster Transformers for Natural Language Processing

A summary of promising directions from ICLR 2020 for better and faster pretrained tranformers language models.

Recent & Upcoming Talks

Neural Language Models: the New Frontier of Natural Language Understanding
The Literary Ordnance: When the Writer is an AI
Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks



Covid-19 Semantic Browser

A semantic browser for SARS-CoV-2 and COVID-19 powered by neural language models.

AItalo Svevo: Letters from an Artificial Intelligence

Generating letters with a neural language model in the style of Italo Svevo, a famous italian writer of the 20th century.

Histopathologic Cancer Detection with Neural Networks

A journey into the state of the art of histopathologic cancer detection approaches.