--- title: "Tanja Bergmann — author profile and papers" description: "Tanja Bergmann: 2 papers on Elamur Research (2019), h-index 4 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/tanja-bergmann/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/tanja-bergmann/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Tanja Bergmann # Tanja Bergmann Tanja Bergmann works in natural language processing. The papers here focus on word representations and how they serve sequence labelling tasks such as [named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/). Both deal with contextual embeddings computed at the character level. They also take up a practical question: how different kinds of embedding can be combined and reused inside one model without redesigning it each time. The most cited of these works, [FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP](https://md.research.elamur.ai/free/en/papers/akbik-2019-flair-easy-use-framework-state/) (2019), presents a Python library built on PyTorch. It places many embedding types, including GloVe, ELMo, BERT and Flair's own, behind one common interface. A single architecture can then draw on any of them, alone or stacked together, with no extra engineering. The second paper, [Pooled Contextualized Embeddings for Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/akbik-2019-pooled-contextualized-embeddings-named-entity/) (2019), targets rare names that occur in sentences offering little context. It stores the contextual vectors seen for each distinct string as a dataset is processed and pools them by mean, minimum or maximum into a global vector. That vector is then joined to the current contextual embedding, and the method is illustrated on CoNLL-03 examples. Both papers date from 2019, so the most influential and the most recent work here are the same. Together they show the method and its software in tandem: a refinement of character-based contextual embeddings for entity tagging, alongside a framework that makes such embeddings easy to combine with others. The FLAIR library itself comes from Zalando Research. Bergmann's co-authors on these papers are [Alan Akbik](https://md.research.elamur.ai/free/en/authors/alan-akbik/) and [Roland Vollgraf](https://md.research.elamur.ai/free/en/authors/roland-vollgraf/), who appear on both, along with [Duncan Blythe](https://md.research.elamur.ai/free/en/authors/duncan-blythe/) and [Stefan Schweter](https://md.research.elamur.ai/free/en/authors/stefan-schweter/). Earlier bylines list the Hasso Plattner Institute in Potsdam, Germany, between 2013 and 2015. 2 papers on this site · 2019 Tanja Bergmann has 2 papers on this site, in 2019, most of them on [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/); often with [Alan Akbik](https://md.research.elamur.ai/free/en/authors/alan-akbik/), [Roland Vollgraf](https://md.research.elamur.ai/free/en/authors/roland-vollgraf/), [Duncan Blythe](https://md.research.elamur.ai/free/en/authors/duncan-blythe/). [OpenAlex](https://openalex.org/A5028075850) · [**h-index 4**](https://openalex.org/authors/A5028075850) · [5 works](https://openalex.org/works?filter=author.id:A5028075850) · [738 citations](https://openalex.org/works?filter=author.id:A5028075850&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/tanja-bergmann/#papers) · [401 citations in our library](https://md.research.elamur.ai/free/en/authors/tanja-bergmann/cited-by/) 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=Tanja+Bergmann) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Tanja+Bergmann) · [dblp](https://dblp.org/search?q=Tanja+Bergmann) · [ACL Anthology](https://aclanthology.org/search/?q=Tanja+Bergmann) ## Affiliations - [Hasso Plattner Institute](https://md.research.elamur.ai/free/en/labs/hasso-plattner-institute/) · Potsdam, Germany —2013–2015 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Named entity recognition 1](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) ## Works by year ### 2010s [**2019** 2 papers](https://md.research.elamur.ai/free/en/authors/tanja-bergmann/year/2019/) ## Papers The most cited first (OpenAlex and our library). 1. **[FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP](https://md.research.elamur.ai/free/en/papers/akbik-2019-flair-easy-use-framework-state/)** *(2019 · 645 citations)* Modern word representations, such as character-level features and contextualized language-model embeddings, usually cannot be plugged into a model the way classic vectors can. 2. **[Pooled Contextualized Embeddings for Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/akbik-2019-pooled-contextualized-embeddings-named-entity/)** *(2019 · 385 citations)* Contextual string embeddings, the character-level method behind Flair (Akbik et al., 2018), can embed any word in its context. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Alan Akbik](https://md.research.elamur.ai/free/en/authors/alan-akbik/) ×2 - [Roland Vollgraf](https://md.research.elamur.ai/free/en/authors/roland-vollgraf/) ×2 - [Duncan Blythe](https://md.research.elamur.ai/free/en/authors/duncan-blythe/) - [Stefan Schweter](https://md.research.elamur.ai/free/en/authors/stefan-schweter/) ## Cited by Papers of our library cite their works 401 times (of the 140 884 papers whose bibliographies we read); [23 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/tanja-bergmann/cited-by/).