--- title: "Roman Grundkiewicz — author profile and papers" description: "Roman Grundkiewicz, Microsoft (United States): 8 papers on Elamur Research (2016–2026), h-index 18 — affiliations, topics, co-authors and who cites them…" canonical: "https://research.elamur.ai/free/en/authors/roman-grundkiewicz/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/roman-grundkiewicz/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Roman Grundkiewicz # Roman Grundkiewicz 8 papers on this site · 2016–2026 current affiliation [Microsoft (United States)](https://ror.org/00d0nc645), Redmond, United States Roman Grundkiewicz has 8 papers on this site, in 2016–2026, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); often with [Eleftherios Avramidis](https://md.research.elamur.ai/free/en/authors/eleftherios-avramidis/), [Tom Kocmi](https://md.research.elamur.ai/free/en/authors/tom-kocmi/), [Ondřej Bojar](https://md.research.elamur.ai/free/en/authors/ondrej-bojar/). [OpenAlex](https://openalex.org/A5023392498) · [**h-index 18**](https://openalex.org/authors/A5023392498) · [67 works](https://openalex.org/works?filter=author.id:A5023392498) · [1 310 citations](https://openalex.org/works?filter=author.id:A5023392498&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [8 works on this site](https://md.research.elamur.ai/free/en/authors/roman-grundkiewicz/#papers) · [1 616 citations in our library](https://md.research.elamur.ai/free/en/authors/roman-grundkiewicz/cited-by/) · 10 more works in our library The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Roman+Grundkiewicz) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Roman+Grundkiewicz) · [dblp](https://dblp.org/search?q=Roman+Grundkiewicz) · [ACL Anthology](https://aclanthology.org/search/?q=Roman+Grundkiewicz) ## Affiliations - [Microsoft (United States)](https://ror.org/00d0nc645) · Redmond, United States —current · 2018–2026 on 18 papers - [Microsoft (United Kingdom)](https://ror.org/01rw27z95) · Reading, United Kingdom —2023–2025 on 7 papers - [Charles University](https://ror.org/024d6js02) · Prague, Czechia —2020–2022 on 2 papers - [University of Edinburgh](https://ror.org/01nrxwf90) · Edinburgh, United Kingdom —2017–2020 on 14 papers - [Adam Mickiewicz University in Poznań](https://ror.org/04g6bbq64) · Poznan, Poland —2013–2018 on 8 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Topics [Machine translation 8](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Evaluation & benchmarks 6](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) ## Papers The most cited first (OpenAlex and our library). 1. **[Marian: Fast Neural Machine Translation in C++](https://md.research.elamur.ai/free/en/papers/junczys-2018-dowmunt-marian-fast-neural-machine-translation/)** *(2018 · 506 citations)* Most neural machine translation toolkits rely on Python and general-purpose deep-learning libraries, which can make them slower and harder to optimize. 2. **[Findings of the 2020 Conference on Machine Translation (WMT20)](https://md.research.elamur.ai/free/en/papers/barrault-2020-findings-2020-conference-machine-translation/)** *(2020 · 401 citations)* This report describes two shared tasks run at WMT20, held online alongside EMNLP 2020. The tasks benchmark current machine translation (MT) systems on common, newly built test data. In the news task, teams built systems for 11 language pairs, which the paper counts as 22 translation directions. The pairs span high-… 3. **[Findings of the WMT24 General Machine Translation Shared Task: The LLM Era Is Here but MT Is Not Solved Yet](https://md.research.elamur.ai/free/en/papers/kocmi-2024-findings-wmt24-general-machine-translation/)** *(2024 · 177 citations)* This WMT24 overview examines how well current translation systems, now increasingly built on large language models, handle varied, realistic input. 4. **[Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing](https://md.research.elamur.ai/free/en/papers/dowmunt-2016-log-linear-combinations-monolingual-bilingual/)** *(2016 · 86 citations)* The paper tackles automatic post-editing (APE): repairing the output of an unseen machine translation system (English→German, IT domain) in the WMT 2016 shared task. 5. **[Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation](https://md.research.elamur.ai/free/en/papers/kocmi-2024-error-span-annotation-balanced-approach/)** *(2024 · 83 citations)* Human evaluation remains the reference standard for judging machine translation, but current protocols involve a trade-off. 6. **[Findings of the WMT25 General Machine Translation Shared Task: Time to Stop Evaluating on Easy Test Sets](https://md.research.elamur.ai/free/en/papers/kocmi-2025-findings-wmt25-general-machine-translation/)** *(2025 · 73 citations)* The WMT25 General Machine Translation shared task asks how well current MT systems, now mostly LLM-based, handle demanding, realistic input. 7. **[Findings of the Second WMT Shared Task on Sign Language Translation (WMT-SLT23)](https://md.research.elamur.ai/free/en/papers/muller-2023-findings-second-wmt-shared-task/)** *(2023 · 39 citations)* WMT-SLT23, the second edition of the WMT shared task on sign language translation, asks systems to translate between signed and spoken languages. 8. **[PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation](https://md.research.elamur.ai/free/en/papers/proietti-2026-pear-pairwise-evaluation-automatic-relative/)** *(2026 · 1 citation)* Most machine translation metrics, including reference-free quality estimation (QE) models, rate each hypothesis on its own and return an absolute number. ## Also in our library 10 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 34 co-authors with a page, the most papers together first. - [Eleftherios Avramidis](https://md.research.elamur.ai/free/en/authors/eleftherios-avramidis/) ×4 - [Tom Kocmi](https://md.research.elamur.ai/free/en/authors/tom-kocmi/) ×4 - [Ondřej Bojar](https://md.research.elamur.ai/free/en/authors/ondrej-bojar/) ×3 - [Anton Dvorkovich](https://md.research.elamur.ai/free/en/authors/anton-dvorkovich/) ×2 - [Barry Haddow](https://md.research.elamur.ai/free/en/authors/barry-haddow/) ×2 - [Christian Federmann](https://md.research.elamur.ai/free/en/authors/christian-federmann/) ×2 - [Marcin Junczys-Dowmunt](https://md.research.elamur.ai/free/en/authors/marcin-junczys-dowmunt/) ×2 - [Mark Fishel](https://md.research.elamur.ai/free/en/authors/mark-fishel/) ×2 - [Markus Freitag](https://md.research.elamur.ai/free/en/authors/markus-freitag/) ×2 - [Marzena Karpinska](https://md.research.elamur.ai/free/en/authors/marzena-karpinska/) ×2 - [Rachel Bawden](https://md.research.elamur.ai/free/en/authors/rachel-bawden/) ×2 - [Thamme Gowda](https://md.research.elamur.ai/free/en/authors/thamme-gowda/) ×2 ## Cited by Papers of our library cite their works 1 616 times (of the 140 884 papers whose bibliographies we read); [131 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/roman-grundkiewicz/cited-by/).