🧑‍🔬 Nuno M. Guerreiro

Affiliations

• Instituto de Telecomunicações · Lisbon, Portugal — 2021–2023 on 7 papers
• Instituto Superior Técnico · Lisbon, Portugal — 2019–2023 on 6 papers
• University of Lisbon · Lisbon, Portugal — 2019–2023 on 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

Topics

Machine translation5Multilingual & cross-lingual NLP3Evaluation & benchmarks2Language models & pretraining1

Papers

The most cited first (OpenAlex and our library).

1. xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection (2024 · 333 citations)
   Neural metrics for machine translation evaluation, such as COMET and BLEURT, usually output one sentence-level number.
2. CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task (2022 · 325 citations)
   This paper describes the joint IST and Unbabel entry to the WMT 2022 Quality Estimation shared task. Quality Estimation (QE) scores machine translation output without reference translations. The team entered all three subtasks: sentence- and word-level quality prediction, Explainable QE, and Critical Error Detection.
3. Hallucinations in Large Multilingual Translation Models (2023 · 244 citations)
   Earlier studies of hallucinations in machine translation, meaning outputs that lose their connection to the source, looked almost only at small bilingual systems (under 100M parameters) for a single high-resource, English-centric pair.
4. Tower: An Open Multilingual Large Language Model for Translation-Related Tasks (2024 · 226 citations)
   Open LLMs, which are mostly trained on English, have so far matched closed systems only when tuned for one translation-related task.
5. Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation (2023 · 147 citations)
   Hallucinations in NMT are rare but severe: translations whose content drifts away from the source. Earlier studies mostly made them more frequent artificially, through noisy data, perturbed inputs or domain shift. They also used inconsistent definitions and seldom checked whether their detectors actually work.…
6. Scaling up CometKiwi: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task (2023 · 135 citations)
   Quality Estimation (QE) scores machine translation output without a reference translation. This paper describes the Unbabel–IST entry to the WMT 2023 QE shared task. Task 1 asked for quality predictions at both the sentence and word level, while Task 2 required pinpointing individual error spans and labelling each…
7. EuroLLM: Multilingual Language Models for Europe (2024 · 131 citations)
   Open-weight LLMs such as LLaMA, Mistral and Gemma mostly serve English and a few major languages, leaving many European languages underserved.
8. Findings of the WMT 2023 Shared Task on Quality Estimation (2023 · 129 citations)
   The WMT 2023 Quality Estimation shared task benchmarks systems that judge neural MT output without reference translations, at both sentence and word level.

Also in our library

2 more works of theirs are in our library without a page here yet; they will appear as we publish them.

Co-authors here

12 of 26 co-authors with a page, the most papers together first.

• André F. T. Martins ×6
• Ricardo Rei ×6
• José G. C. de Souza ×4
• Pierre Colombo ×4
• Duarte M. Alves ×3
• Jose Pombal ×3
• Luisa Coheur ×3
• Amin Farajian ×2
• Barry Haddow ×2
• Chrysoula Zerva ×2
• Daan van Stigt ×2
• Joao Alves ×2

Cited by

Papers of our library cite their works 1 356 times (of the 140 884 papers whose bibliographies we read); 105 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/nuno-m-guerreiro/