Elamur Research⌕
☰
home / authors / Gabriele Sarti

Gabriele Sarti

Gabriele Sarti has 2 papers in our library, in 2023–2026, most of them on Interpretability, Machine translation; often with Arianna Bisazza, Malvina Nissim.

2 papers in our library · 2023–2026

OpenAlex · ORCID · h-index 8 · 39 works · 221 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 348 times in our library · 6 more in our library without a page yet · ⭐ Paper Stars ranking: #5101

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University of GroningenGroningen · Netherlands2021–2026 · 21 papersEducation 2021–2025 · PhD in Computational Linguistics, Center for Language and CognitionEmployment until 2025current🎓Northeastern UniversityBoston · United States2026 · 4 papersEmployment 2026 · Postdoctoral Researcher, Khoury College of Computer Sciencescurrent🎓Scuola Internazionale Superiore di Studi AvanzatiTrieste · Italy2020–2021 · 7 papers🎓University of TriesteTrieste · Italy2018–2021 · 7 papersEducation 2018–2020 · MSc in Data Science and Scientific Computing, Department of Mathematics and Geosciences🔬Institute for Computational Linguistics “A. Zampolli”Pisa · Italy2021–2022 · 2 papers
🏛️ParallaxLondon · United Kingdom2026Employment since 2026 · Co-founder and Technical Director
🏛️Amazon AWS AI LabsNew York · United States2022Employment 2022 · Applied Scientist Intern, Machine Translation
🏛️Aindo S.r.l.Trieste · Italy2021Employment 2021 · Research Scientist
🎓Cegep de Saint HyacintheSaint-Hyacinthe · Canada2015–2018Education 2015–2018 · Collegial Studies Degree in Informatics and Management, Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksBiochemistry, Genetics and Molecular Biology · 1 workMolecular Biology · 1 work

🧭 Topics 2Research subjects and languages the work is about.Interpretability · 2 worksMachine translation · 1 work

 Works by year

2020s

20261 paperFrom Insights to Impact: Actionable Interpretability for Neural Machine Translation20231 paperInseq: An Interpretability Toolkit for Sequence Generation Models

 Papers

The most cited first (OpenAlex and our library).

  1. Inseq: An Interpretability Toolkit for Sequence Generation Models (2023 · 96 citations)
    Most feature attribution research and tooling in NLP targets classification, where each input token gets a single importance score.
  2. From Insights to Impact: Actionable Interpretability for Neural Machine Translation (2026)
    This EAMT 2026 thesis abstract tackles a persistent disconnect: interpretability research reveals much about how language models work internally, yet those findings seldom benefit the people who actually use machine translation.

All works

8 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Inseq: An Interpretability Toolkit for Sequence Generation ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Gabriele Sarti, Nils Feldhus, Ludwig Sickert, et al.2023 · 96 citations
  2. A Primer on the Inner Workings of Transformer-based Language ModelsarXiv:2405.00208 · original ↗ · no summary yetJavier Ferrando et al.2024 · 72 citations
  3. DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse LanguagesProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · original ↗ · no summary yetGabriele Sarti et al.2022 · 20 citations
  4. Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine TranslationTransactions of the Association for Computational Linguistics · original ↗ · no summary yetLukas Edman et al.2024 · 17 citations
  5. QE4PE: Word-level Quality Estimation for Human Post-EditingTransactions of the Association for Computational Linguistics · original ↗ · no summary yetGabriele Sarti et al.2025 · 11 citations
  6. Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreementProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · original ↗ · no summary yetGabriele Sarti et al.2025 · 6 citations
  7. Steering Large Language Models for Machine Translation PersonalizationProceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetDaniel Scalena et al.2026 · 3 citations
  8. From Insights to Impact: Actionable Interpretability for Neural Machine TranslationAnnual Conference of the European Association for Machine Translation (EAMT)Gabriele Sarti2026

 Co-authors here

2 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 348 times (of the 141,840 papers whose bibliographies we read); 28 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/gabriele-sarti/