--- title: "Johannes Leveling — author profile and papers" description: "Johannes Leveling, Fraunhofer Institute for Intelligent Analysis and Information Systems: 2 papers on Elamur Research (2014–2024), h-index 14 —…" canonical: "https://research.elamur.ai/free/en/authors/johannes-leveling/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/johannes-leveling/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Johannes Leveling # Johannes Leveling Johannes Leveling works in natural language processing, with papers here on [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), multilingual language technology and the pretraining of large language models. A recurring concern is how system choices and evaluation settings shape what can be measured, whether through shared benchmarking campaigns or through tightly controlled training experiments that compare languages and model components. The most cited of these papers is the [Findings of the 2014 Workshop on Statistical Machine Translation](https://md.research.elamur.ai/free/en/papers/bojar-2014-findings-2014-workshop-statistical-machine/). It reports the ninth round of an annual campaign that compares translation systems and the methods used to judge them. That year the campaign covered news translation, quality estimation and a newly added medical translation task. The news task paired English with several languages, including Hindi as a distant, low-resource case. Its test sets were rebuilt so that every sentence came from text originally written in one of the two languages of the pair, which reduces artifacts of translated input. The paper was written with a large group of organisers, among them [Ondřej Bojar](https://md.research.elamur.ai/free/en/authors/ondrej-bojar/) and [Philipp Koehn](https://md.research.elamur.ai/free/en/authors/philipp-koehn/). The newer work turns to large language models. [Tokenizer Choice For LLM Training: Negligible or Crucial?](https://md.research.elamur.ai/free/en/papers/ali-2024-tokenizer-choice-llm-training-negligible/) examines whether the [tokenizer](https://md.research.elamur.ai/free/en/topics/tokenization/) behind a decoder-only model affects its quality and training cost. The study varies the algorithm, software library, language coverage and vocabulary size, and trains a separate model for each tokenizer on matched English-only and five-language corpora. Co-authors on this paper include [Klaudia Thellmann](https://md.research.elamur.ai/free/en/authors/klaudia-thellmann/). Leveling is currently at the [Fraunhofer Institute for Intelligent Analysis and Information Systems](https://md.research.elamur.ai/free/en/labs/fraunhofer-institute-for-intelligent-analysis-and-information-systems/) in Sankt Augustin, part of the Fraunhofer-Gesellschaft. Earlier bylines point to [Dublin City University](https://md.research.elamur.ai/free/en/universities/dublin-city-university/) and, before that, FernUniversität in Hagen. Johannes Leveling has 2 papers in our library, in 2014–2024, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); often with [Barry Haddow](https://md.research.elamur.ai/free/en/authors/barry-haddow/), [Christian Buck](https://md.research.elamur.ai/free/en/authors/christian-buck/), [Christian Federmann](https://md.research.elamur.ai/free/en/authors/christian-federmann/). 2 papers in our library · 2014–2024 [OpenAlex](https://openalex.org/A5063045515) · [ORCID](https://orcid.org/0000-0003-0603-4191) · [**h-index 14**](https://openalex.org/authors/A5063045515) · [166 works](https://openalex.org/works?filter=author.id:A5063045515) · [1,664 citations](https://openalex.org/works?filter=author.id:A5063045515&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/johannes-leveling/#papers) · [🔗 466 citations in our library](https://md.research.elamur.ai/free/en/authors/johannes-leveling/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #1961](https://md.research.elamur.ai/free/en/paper-stars/page/20/#star-1961) 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=Johannes+Leveling) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Johannes+Leveling) · [dblp](https://dblp.org/search?q=Johannes+Leveling) · [ACL Anthology](https://aclanthology.org/search/?q=Johannes+Leveling) ## Affiliations [🔬**Fraunhofer Institute for Intelligent Analysis and Information Systems** Sankt Augustin · Germany 2023–2026 · 7 papers*current*](https://md.research.elamur.ai/free/en/labs/fraunhofer-institute-for-intelligent-analysis-and-information-systems/) · [🏛️**Fraunhofer-Gesellschaft** Munich · Germany 2026 · 1 paper*current*](https://ror.org/05hkkdn48) · [🎓**Dublin City University** Dublin · Ireland 2009–2018 · 73 papers](https://md.research.elamur.ai/free/en/universities/dublin-city-university/) · [🎓**FernUniversität in Hagen** Hagen · Germany 2004–2008 · 21 papers](https://ror.org/04tkkr536) · [🏢**Elsevier BV** Amsterdam · Netherlands 2015 · 2 papers](https://ror.org/013fhv752) 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 (1)](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Language models & pretraining (1)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Multilingual & cross-lingual NLP (1)](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Evaluation & benchmarks (1)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Tokenization & segmentation (1)](https://md.research.elamur.ai/free/en/topics/tokenization/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/ali-2024-tokenizer-choice-llm-training-negligible/) ### 2010s [**2014** 1 paper](https://md.research.elamur.ai/free/en/papers/bojar-2014-findings-2014-workshop-statistical-machine/) ## Papers The most cited first (OpenAlex and our library). 1. **[Findings of the 2014 Workshop on Statistical Machine Translation](https://md.research.elamur.ai/free/en/papers/bojar-2014-findings-2014-workshop-statistical-machine/)** *(2014 · 923 citations)* WMT14 is the ninth edition of an annual shared-task campaign that benchmarks machine translation and the methods used to evaluate it. 2. **[Tokenizer Choice For LLM Training: Negligible or Crucial?](https://md.research.elamur.ai/free/en/papers/ali-2024-tokenizer-choice-llm-training-negligible/)** *(2024 · 102 citations)* Tokenizers are rarely examined when building LLMs. This paper asks whether the choice of tokenizer measurably affects decoder-only model quality and training cost, in both English-only and multilingual settings. The authors built two training corpora of 70B words each, with matched domain mixtures (80% web-crawled… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 12 of 13 co-authors with a page, the most papers together first. - [Barry Haddow](https://md.research.elamur.ai/free/en/authors/barry-haddow/) - [Christian Buck](https://md.research.elamur.ai/free/en/authors/christian-buck/) - [Christian Federmann](https://md.research.elamur.ai/free/en/authors/christian-federmann/) - [Christof Monz](https://md.research.elamur.ai/free/en/authors/christof-monz/) - [Herve Saint-Amand](https://md.research.elamur.ai/free/en/authors/herve-saint-amand/) - [Jan Ebert](https://md.research.elamur.ai/free/en/authors/jan-ebert/) - [Klaudia Thellmann](https://md.research.elamur.ai/free/en/authors/klaudia-thellmann/) - [Lucia Specia](https://md.research.elamur.ai/free/en/authors/lucia-specia/) - [Matt Post](https://md.research.elamur.ai/free/en/authors/matt-post/) - [Ondřej Bojar](https://md.research.elamur.ai/free/en/authors/ondrej-bojar/) - [Pavel Pecina](https://md.research.elamur.ai/free/en/authors/pavel-pecina/) - [Philipp Koehn](https://md.research.elamur.ai/free/en/authors/philipp-koehn/) ## Cited by Papers of our library cite their works 466 times (of the 140,884 papers whose bibliographies we read); [55 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/johannes-leveling/cited-by/).