Post-Editing | Gabriele Sarti

Post-Editing

From Insights to Impact: Actionable Interpretability for Neural Machine Translation

This presentation summarizes the main contributions of my PhD thesis, advocating for a user-centric perspective on interpretability research, aiming to translate theoretical advances in model understanding in practical benefits in trustworthiness and transparency for end users of these systems.

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.

QE4PE: Word-level Quality Estimation for Human Post-Editing

We investigate the impact of word-level quality estimation on MT post-editing with 42 professional post-editors.

DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages

DivEMT is a publicly available post-editing study of Neural Machine Translation over a typologically diverse set of target languages.