7 | Gabriele Sarti

7

From Insights to Impact: Actionable Interpretability for Neural Machine Translation

This dissertation bridges the gap between scientific insights into how language models work and practical benefits for users of these systems, paving the way for better human-AI interaction practices for professional translators and everyday users worldwide.

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 neural language models' learned representations.