---
title: "Denmark — research institutions, scientists and papers"
description: "Denmark: 7 institutions with papers in our library in 3 agglomerations, 38 people with a page, 79 works, 16,666 citations."
canonical: "https://research.elamur.ai/free/en/countries/denmark/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/denmark/)

[home](https://md.research.elamur.ai/free/en/) / [countries](https://md.research.elamur.ai/free/en/countries/) / Denmark

# Denmark

Country 7 institutions in 3 agglomerations · [all countries](https://md.research.elamur.ai/free/en/countries/)

[**7** institutions with a page](https://md.research.elamur.ai/free/en/countries/denmark/#institutions) · [**3** agglomerations](https://md.research.elamur.ai/free/en/countries/denmark/#agglomerations) · [**38** people with a page](https://md.research.elamur.ai/free/en/countries/denmark/#authors) · [**79** works in our library](https://md.research.elamur.ai/free/en/countries/denmark/#works) · [**16,666** citations of their works](https://md.research.elamur.ai/free/en/countries/denmark/#works)

## About

### Profile

Denmark appears on this site through a small group of research institutions in three city regions. The [Copenhagen](https://md.research.elamur.ai/free/en/agglomerations/copenhagen/) region holds most of them: the [University of Copenhagen](https://md.research.elamur.ai/free/en/universities/university-of-copenhagen/), the [IT University of Copenhagen](https://md.research.elamur.ai/free/en/universities/it-university-of-copenhagen/), [Copenhagen Business School](https://md.research.elamur.ai/free/en/universities/copenhagen-business-school/), [Copenhagen University Hospital](https://md.research.elamur.ai/free/en/hospitals/copenhagen-university-hospital/) and, in Kongens Lyngby to the north, the [Technical University of Denmark](https://md.research.elamur.ai/free/en/universities/technical-university-of-denmark/). Outside the capital, [Aalborg University](https://md.research.elamur.ai/free/en/universities/aalborg-university/) represents [Aalborg](https://md.research.elamur.ai/free/en/agglomerations/aalborg/), and the [University of Southern Denmark](https://md.research.elamur.ai/free/en/universities/university-of-southern-denmark/) represents [Odense](https://md.research.elamur.ai/free/en/agglomerations/odense/). All of these are universities except the hospital.

The Danish works here have a clear subject. Almost all of them belong to [natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/) and [linguistics](https://md.research.elamur.ai/free/en/shelves/linguistics/). Within that area they cover multilingual and low-resource language technology, hate speech and sentiment, fact checking and misinformation, evaluation, the inner workings of pretrained language models, legal language and the cultural dimension of language systems. The University of Copenhagen produced most of these works and most of the citations they attract. The IT University of Copenhagen is a substantial second centre. The other institutions add smaller groups of papers, and several of those papers are well cited.

### History

The earliest Danish work in our library is [Generation of VP Ellipsis: A Corpus-Based Approach](https://md.research.elamur.ai/free/en/papers/hardt-2001-generation-vp-ellipsis-corpus-based/) from 2001, associated with Copenhagen Business School. It studies when a text generator should drop a verb phrase and keep only the auxiliary verb. Ellipsis stayed a lasting interest of the business school. In 2016 came [Antecedent Selection for Sluicing: Structure and Content](https://md.research.elamur.ai/free/en/papers/anand-2016-antecedent-selection-sluicing-structure-content/), which argues that both syntax and discourse help find what an elided question refers to. In 2021 [Ellipsis Resolution as Question Answering](https://md.research.elamur.ai/free/en/papers/aralikatte-2021-ellipsis-resolution-as-question-answering/) recast the problem for BERT-based models.

In 2014 a clinical text-mining paper appeared, [Negation scope and spelling variation for text-mining of Danish electronic patient records](https://md.research.elamur.ai/free/en/papers/thomas-2014-negation-scope-spelling-variation-text/). It is shared by the Technical University of Denmark, Copenhagen University Hospital and the University of Southern Denmark. It describes a simple dictionary matcher for ICD-10 codes in Danish psychiatric records, and it is one of the few Danish works here that deal directly with the Danish language.

The main growth comes in 2016. That year brought the most cited Danish work on the site, on hate speech detection on Twitter. It also brought a position paper on the social impact of language technology, a study of multi-task learning in which simple tasks are supervised at lower layers of a deep network, a multilingual part-of-speech tagger, and a method for parsing truly low-resource languages by projecting annotation across many languages. Work from 2017 and 2018 continued these lines. It learned emotional representations from emoji, asked which task pairs help each other in multi-task learning, chose source parsers for low-resource languages, and tested the limits of unsupervised bilingual dictionary induction.

From 2019 the range widens. Fact checking and rumour verification appear, along with a large parallel corpus for low-resource languages. In 2020 came an influential survey of what is known about BERT, along with work on explainability and on Danish offensive language. Legal language understanding, disagreement in evaluation and a multi-task toolkit followed in 2021. Cross-cultural NLP and stance detection came in 2022. From 2023 the works increasingly concern large language models: clinical summarisation, factuality, cultural alignment, multilingual instruction tuning and very hard benchmarks. The most recent works here date from 2025.

### Research profile

The largest topical strand is [multilingual and cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/), joined by work on [low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) and [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/). [Multilingual Projection for Parsing Truly Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/agic-2016-multilingual-projection-parsing-truly-low/) and [Cross-Lingual Parser Selection for Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/agic-2017-cross-lingual-parser-selection-low/) both tackle languages that lack annotated treebanks. The second proposes a lightweight way to pick the best source language at run time. [JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/agic-2019-jw300-wide-coverage-parallel-corpus/) responds to the shortage of parallel text by assembling a broad multilingual corpus. [On the Limitations of Unsupervised Bilingual Dictionary Induction](https://md.research.elamur.ai/free/en/papers/sogaard-2018-limitations-unsupervised-bilingual-dictionary-induction/) shows where adversarial methods for building dictionaries without supervision break down. In 2024 [Multilingual Gradient Word-Order Typology from Universal Dependencies](https://md.research.elamur.ai/free/en/papers/baylor-2024-multilingual-gradient-word-order-typology/) from Aalborg proposed continuous rather than categorical word-order features. That same year, [Aya Dataset](https://md.research.elamur.ai/free/en/papers/singh-2024-aya-dataset-open-access-collection/) gathered instruction-tuning examples beyond English.

[Sentiment and emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) is the second strand, and it is closely tied to research on abusive language. [Hateful Symbols or Hateful People?](https://md.research.elamur.ai/free/en/papers/waseem-2016-hateful-symbols-or-hateful-people/) builds predictive features for racist and sexist tweets. [Are You a Racist or Am I Seeing Things?](https://md.research.elamur.ai/free/en/papers/waseem-2016-are-you-racist-or-am/) asks how much annotators' expertise shapes labels gathered by crowdsourcing. [Using millions of emoji occurrences](https://md.research.elamur.ai/free/en/papers/felbo-2017-millions-emoji-occurrences-learn-any/) uses emoji in social media text as a weak signal to learn representations for sentiment, emotion and sarcasm, tasks for which labelled material is scarce. [Offensive Language and Hate Speech Detection for Danish](https://md.research.elamur.ai/free/en/papers/sigurbergsson-2020-offensive-language-hate-speech-detection/) builds the first such Danish resource, according to its authors.

A third strand covers fact checking and misinformation. It includes [MultiFC](https://md.research.elamur.ai/free/en/papers/augenstein-2019-multifc-real-world-multi-domain/), a collection of real claims from many domains, and [SemEval-2019 Task 7: RumourEval](https://md.research.elamur.ai/free/en/papers/gorrell-2019-semeval-2019-task-7-rumoureval/), a shared benchmark for rumour veracity and stance. Also part of it are [Generating Fact Checking Explanations](https://md.research.elamur.ai/free/en/papers/atanasova-2020-generating-fact-checking-explanations/), [A Survey on Stance Detection for Mis- and Disinformation Identification](https://md.research.elamur.ai/free/en/papers/hardalov-2022-survey-stance-detection-mis-disinformation/) and [Factuality Challenges in the Era of Large Language Models](https://md.research.elamur.ai/free/en/papers/augenstein-2023-factuality-challenges-era-large-language/).

[Evaluation and benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) form a fourth line. [We Need to Consider Disagreement in Evaluation](https://md.research.elamur.ai/free/en/papers/basile-2021-we-need-consider-disagreement-evaluation/) challenges scoring against a single aggregated gold label. [LexGLUE](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-lexglue-benchmark-dataset-legal-language/) sets up a benchmark for English legal text and anchors the [legal AI](https://md.research.elamur.ai/free/en/topics/legal-ai/) topic. [Humanity's Last Exam](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/) responds to near-saturated benchmarks with much harder questions. [Findings of the WMT25 General Machine Translation Shared Task](https://md.research.elamur.ai/free/en/papers/kocmi-2025-findings-wmt25-general-machine-translation/) evaluates translation systems that are now mostly built on large models.

Methods for representation learning make up a further line. [Deep multi-task learning with low level tasks supervised at lower layers](https://md.research.elamur.ai/free/en/papers/sogaard-2016-deep-multi-task-learning-low/) offers a way to combine cascaded pipelines with shared representations. [Identifying beneficial task relations](https://md.research.elamur.ai/free/en/papers/bingel-2017-identifying-beneficial-task-relations-multi/) predicts which auxiliary tasks help, using features of single-task learning curves. [MaChAmp](https://md.research.elamur.ai/free/en/papers/goot-2021-massive-choice-ample-tasks-machamp/) packages multi-task learning into a toolkit configured through a simple file. [Neural Unsupervised Domain Adaptation in NLP](https://md.research.elamur.ai/free/en/papers/ramponi-2020-neural-unsupervised-domain-adaptation-nlp/) surveys adaptation across text varieties. Work on [language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) and [interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/) is led by [A Primer in BERTology](https://md.research.elamur.ai/free/en/papers/rogers-2020-primer-bertology-what-we-know/) and [A Diagnostic Study of Explainability Techniques for Text Classification](https://md.research.elamur.ai/free/en/papers/atanasova-2020-diagnostic-study-explainability-techniques-text/).

Smaller lines cover [bias, fairness and safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), which includes [The Social Impact of Natural Language Processing](https://md.research.elamur.ai/free/en/papers/hovy-2016-social-impact-natural-language-processing/) and the cross-cultural studies. Other small lines cover [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), discourse and ellipsis, and [Hebrew and Aramaic](https://md.research.elamur.ai/free/en/topics/hebrew-aramaic/). The last of these is represented by [Dating ancient manuscripts using radiocarbon and AI-based writing style analysis](https://md.research.elamur.ai/free/en/papers/popovic-2024-dating-ancient-manuscripts-using-radiocarbon/), which dates Dead Sea Scrolls by their handwriting. Clinical language processing appears in [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://md.research.elamur.ai/free/en/papers/veen-2023-adapted-large-language-models-outperform/).

### Leading scientists

[Dirk Hovy](https://md.research.elamur.ai/free/en/authors/dirk-hovy/), at the University of Copenhagen, comes first among the Danish researchers on this site. Hovy co-wrote the most cited Danish work, on predictive features for hate speech on Twitter. Hovy also co-wrote the 2016 paper that brought the ethics of technology into NLP and grouped the possible harms of language systems into categories.

[Anders Søgaard](https://md.research.elamur.ai/free/en/authors/anders-sogaard/), also at the University of Copenhagen and connected with Copenhagen Business School, has a wide body of work here. It includes multi-task learning with Yoav Goldberg, task relations with Joachim Bingel, the emoji representation study, the multilingual part-of-speech tagger and the critique of unsupervised bilingual dictionary induction with Sebastian Ruder and Ivan Vulić.

[Ilias Chalkidis](https://md.research.elamur.ai/free/en/authors/ilias-chalkidis/), of the University of Copenhagen, led LexGLUE, the legal-language benchmark that is central to the legal AI work here.

[Isabelle Augenstein](https://md.research.elamur.ai/free/en/authors/isabelle-augenstein/), at the University of Copenhagen and also connected with Aalborg University, works on automatic fact checking. Augenstein's papers here include MultiFC and the 2023 overview of factuality problems raised by large language models.

[Anna Rogers](https://md.research.elamur.ai/free/en/authors/anna-rogers/), linked with both the University of Copenhagen and the IT University of Copenhagen, is the first author of the BERTology primer. That survey reviews what probing studies reveal about BERT and the proposed changes to its training and architecture.

[Barbara Plank](https://md.research.elamur.ai/free/en/authors/barbara-plank/), at the IT University of Copenhagen, worked on multilingual tagging, cross-lingual projection parsing and the domain adaptation survey with Alan Ramponi. That survey builds on Plank's notion of a space of text varieties.

[Leon Derczynski](https://md.research.elamur.ai/free/en/authors/leon-derczynski/) is at the IT University of Copenhagen. Its works in our library include the RumourEval shared task and the Danish offensive language study.

[Daniel Hershcovich](https://md.research.elamur.ai/free/en/authors/daniel-hershcovich/), at the University of Copenhagen, is the first author of Challenges and Strategies in Cross-Cultural NLP. The paper sets out several dimensions along which cultures differ and along which language systems may carry cultural bias. The same concern runs through the 2023 study that probes ChatGPT with the Hofstede Culture Survey.

[Desmond Elliott](https://md.research.elamur.ai/free/en/authors/desmond-elliott/) of the University of Copenhagen belongs to the university's language-and-vision side. Among the Danish works this side appears through the third shared task on [multimodal machine translation](https://md.research.elamur.ai/free/en/papers/barrault-2018-findings-third-shared-task-multimodal/) and the vision and language topic.

[Anuj Pareek](https://md.research.elamur.ai/free/en/authors/anuj-pareek/) represents Copenhagen University Hospital. Its works here are the study of adapted large language models for clinical summarisation and the earlier Danish patient-record text-mining paper.

[Christina Lioma](https://md.research.elamur.ai/free/en/authors/christina-lioma/), at the University of Copenhagen and also connected with the Technical University of Denmark, co-wrote MultiFC and both of Pepa Atanasova's 2020 papers on explaining classifiers and fact-checking verdicts.

[Ruixiang Cui](https://md.research.elamur.ai/free/en/authors/ruixiang-cui/) of the University of Copenhagen completes the first group of researchers.

Beyond these, [Željko Agić](https://md.research.elamur.ai/free/en/authors/zeljko-agic/) of the IT University of Copenhagen built JW300 and the low-resource parsing methods. [Rob van der Goot](https://md.research.elamur.ai/free/en/authors/rob-van-der-goot/) led MaChAmp, and [Daniel Hardt](https://md.research.elamur.ai/free/en/authors/daniel-hardt/) of Copenhagen Business School wrote the early ellipsis-generation paper. [Johannes Bjerva](https://md.research.elamur.ai/free/en/authors/johannes-bjerva/) and [Heather Lent](https://md.research.elamur.ai/free/en/authors/heather-lent/) are at Aalborg University, and [Eckhard Bick](https://md.research.elamur.ai/free/en/authors/eckhard-bick/) is at the University of Southern Denmark.

### Landmark works

The most cited Danish work in our library is the 2016 study of hate speech on Twitter by Zeerak Waseem and Dirk Hovy. It asks whether user characteristics add to word features when detecting racist and sexist tweets, and it provided an annotated corpus that many later studies used. Close behind is the BERTology primer by Anna Rogers, Olga Kovaleva and Anna Rumshisky. It became a common reference for what pretrained transformers learn.

Next comes the 2023 clinical summarisation paper from the hospital side. It shows that suitably adapted large language models can produce summaries of medical records that clinicians often prefer to expert ones, which addresses the time clinicians lose to writing such summaries. Waseem's study of annotator influence follows, then the emoji paper, the multi-task learning paper of Søgaard and Goldberg, and the social impact paper of Hovy and Shannon L. Spruit.

The next group of highly cited works shows how wide the Danish research is. It includes the dictionary induction critique, JW300, the domain adaptation survey, MultiFC, the task-relations study, RumourEval, the cross-cultural NLP framework and the ChatGPT cultural alignment study. Later and still widely read are LexGLUE, the factuality overview, Humanity's Last Exam and the Aya collection for multilingual instruction tuning.

### Labs and units

The Danish research on this site is organised by institution. The University of Copenhagen carries most of it, across hate speech, multi-task learning, fact checking, legal NLP, language model analysis and cross-cultural work. The IT University of Copenhagen concentrates on multilingual and low-resource processing, domain adaptation, evaluation with disagreement, multi-task tooling and Danish abusive language. Copenhagen Business School specialises in ellipsis and discourse, and its people include Daniel Hardt and Nizar Habash.

The Technical University of Denmark appears through the emoji study and the clinical text-mining paper. Copenhagen University Hospital contributes clinical language processing. Aalborg University's works concern hard benchmarks, multilingual instruction tuning and word-order typology. The University of Southern Denmark's works cover machine translation evaluation, manuscript dating and Danish patient records.

### Collaborations

The Danish institutions here are tightly linked to one another. JW300 is shared by the University of Copenhagen and the IT University of Copenhagen, and the emoji paper joins the University of Copenhagen with the Technical University of Denmark. The Aya collection connects the IT University of Copenhagen with Aalborg University. The 2014 patient-record study connects the Technical University of Denmark, Copenhagen University Hospital and the University of Southern Denmark. Several researchers also appear at more than one institution: Søgaard at Copenhagen Business School, Rogers at the IT University, Augenstein at Aalborg and Lioma at the Technical University of Denmark.

Co-authors from abroad appear throughout the most cited works. They include Yoav Goldberg on multi-task learning and tagging, Ivan Vulić on dictionary induction and JW300, and Sebastian Ruder on dictionary induction. Alan Mislove worked on the emoji study, Ion Androutsopoulos and Nikolaos Aletras on LexGLUE, Preslav Nakov on the stance survey, and Timothy Baldwin on the factuality overview. Large community efforts such as RumourEval, the multimodal translation shared task, WMT25, Aya and Humanity's Last Exam place Danish researchers inside broad international teams.

### Timeline

From 2001 to 2014 the Danish works are few and specialised: ellipsis generation at Copenhagen Business School, then text-mining of Danish psychiatric records shared by the technical university, the hospital and Odense.

From 2016 to 2018 the Copenhagen universities produced a dense body of work. Its subjects were hate speech, the social impact of NLP, multi-task learning, multilingual tagging and parsing, emoji-based emotion learning, bilingual dictionary induction and multimodal translation.

Between 2019 and 2021 the main subjects were fact checking and rumours, low-resource parallel corpora, analysis and explanation of neural models, domain adaptation, Danish offensive language, legal benchmarks, disagreement-aware evaluation and multi-task tooling.

From 2022 to 2025 the focus moves to large language models. Work in this period covers cultural alignment and cross-cultural NLP, stance detection, factuality, clinical summarisation, multilingual instruction tuning, word-order typology, manuscript dating, demanding benchmarks and machine translation evaluation. Aalborg and Odense contribute to this period alongside Copenhagen.

## Where

## Agglomerations (3)

1. [**Copenhagen**5 institutions*16,112 citations*](https://md.research.elamur.ai/free/en/agglomerations/copenhagen/)
2. [**Aalborg**1 institution*449 citations*](https://md.research.elamur.ai/free/en/agglomerations/aalborg/)
3. [**Odense**1 institution*105 citations*](https://md.research.elamur.ai/free/en/agglomerations/odense/)

## Institutions (7)

### 🎓 Universities (6)

1. **[University of Copenhagen](https://md.research.elamur.ai/free/en/universities/university-of-copenhagen/)**University · [Copenhagen](https://md.research.elamur.ai/free/en/agglomerations/copenhagen/), Denmark*65 works · 12,760 citations*
2. **[IT University of Copenhagen](https://md.research.elamur.ai/free/en/universities/it-university-of-copenhagen/)**University · [Copenhagen](https://md.research.elamur.ai/free/en/agglomerations/copenhagen/), Denmark*11 works · 1,744 citations*
3. **[Copenhagen Business School](https://md.research.elamur.ai/free/en/universities/copenhagen-business-school/)**University · [Copenhagen](https://md.research.elamur.ai/free/en/agglomerations/copenhagen/), Denmark*3 works · 48 citations*
4. **[Technical University of Denmark](https://md.research.elamur.ai/free/en/universities/technical-university-of-denmark/)**University · [Kongens Lyngby](https://md.research.elamur.ai/free/en/agglomerations/copenhagen/), Denmark*2 works · 626 citations*
5. **[Aalborg University](https://md.research.elamur.ai/free/en/universities/aalborg-university/)**University · [Aalborg](https://md.research.elamur.ai/free/en/agglomerations/aalborg/), Denmark*3 works · 449 citations*
6. **[University of Southern Denmark](https://md.research.elamur.ai/free/en/universities/university-of-southern-denmark/)**University · [Odense](https://md.research.elamur.ai/free/en/agglomerations/odense/), Denmark*3 works · 105 citations*

### 🏥 Hospitals and medical centres (1)

1. **[Copenhagen University Hospital](https://md.research.elamur.ai/free/en/hospitals/copenhagen-university-hospital/)**Hospital · [Copenhagen](https://md.research.elamur.ai/free/en/agglomerations/copenhagen/), Denmark*2 works · 934 citations*

## People (38)

Authors with a page confirmed at its institutions, the most cited first.

1. [**Dirk Hovy**University of Copenhagen*18 papers here · 6,681 citations*](https://md.research.elamur.ai/free/en/authors/dirk-hovy/)
2. [**Anders Søgaard**University of Copenhagen*21 papers here · 4,341 citations*](https://md.research.elamur.ai/free/en/authors/anders-sogaard/)
3. [**Ilias Chalkidis**University of Copenhagen*8 papers here · 4,076 citations*](https://md.research.elamur.ai/free/en/authors/ilias-chalkidis/)
4. [**Isabelle Augenstein**University of Copenhagen*10 papers here · 3,632 citations*](https://md.research.elamur.ai/free/en/authors/isabelle-augenstein/)
5. [**Anna Rogers**University of Copenhagen*3 papers here · 3,304 citations*](https://md.research.elamur.ai/free/en/authors/anna-rogers/)
6. [**Barbara Plank**IT University of Copenhagen*18 papers here · 3,283 citations*](https://md.research.elamur.ai/free/en/authors/barbara-plank/)
7. [**Leon Derczynski**IT University of Copenhagen*6 papers here · 2,650 citations*](https://md.research.elamur.ai/free/en/authors/leon-derczynski/)
8. [**Daniel Hershcovich**University of Copenhagen*8 papers here · 1,687 citations*](https://md.research.elamur.ai/free/en/authors/daniel-hershcovich/)
9. [**Desmond Elliott**University of Copenhagen*5 papers here · 1,565 citations*](https://md.research.elamur.ai/free/en/authors/desmond-elliott/)
10. [**Anuj Pareek**Copenhagen University Hospital*2 papers here · 1,259 citations*](https://md.research.elamur.ai/free/en/authors/anuj-pareek/)
11. [**Christina Lioma**University of Copenhagen*3 papers here · 962 citations*](https://md.research.elamur.ai/free/en/authors/christina-lioma/)
12. [**Ruixiang Cui**University of Copenhagen*2 papers here · 955 citations*](https://md.research.elamur.ai/free/en/authors/ruixiang-cui/)
13. [**Jakob Grue Simonsen**University of Copenhagen*3 papers here · 948 citations*](https://md.research.elamur.ai/free/en/authors/jakob-grue-simonsen/)
14. [**Qiuchi Li**University of Copenhagen*3 papers here · 912 citations*](https://md.research.elamur.ai/free/en/authors/qiuchi-li/)
15. [**Héctor Martínez Alonso**University of Copenhagen*2 papers here · 863 citations*](https://md.research.elamur.ai/free/en/authors/hector-martinez-alonso/)
16. [**Željko Agić**University of Copenhagen*5 papers here · 783 citations*](https://md.research.elamur.ai/free/en/authors/zeljko-agic/)
17. [**Pepa Atanasova**University of Copenhagen*3 papers here · 720 citations*](https://md.research.elamur.ai/free/en/authors/pepa-atanasova/)
18. [**Mike Zhang**IT University of Copenhagen*4 papers here · 698 citations*](https://md.research.elamur.ai/free/en/authors/mike-zhang/)
19. [**Arnav Arora**University of Copenhagen*4 papers here · 596 citations*](https://md.research.elamur.ai/free/en/authors/arnav-arora/)
20. [**Rob van der Goot**IT University of Copenhagen*3 papers here · 595 citations*](https://md.research.elamur.ai/free/en/authors/rob-van-der-goot/)
21. [**Johannes Bjerva**University of Copenhagen*3 papers here · 556 citations*](https://md.research.elamur.ai/free/en/authors/johannes-bjerva/)
22. [**Joachim Bingel**University of Copenhagen*4 papers here · 547 citations*](https://md.research.elamur.ai/free/en/authors/joachim-bingel/)
23. [**Natalie Schluter**University of Copenhagen*2 papers here · 491 citations*](https://md.research.elamur.ai/free/en/authors/natalie-schluter/)
24. [**Chloé Braud**University of Copenhagen*9 papers here · 454 citations*](https://md.research.elamur.ai/free/en/authors/chloe-braud/)
25. [**Mostafa Abdou**University of Copenhagen*2 papers here · 418 citations*](https://md.research.elamur.ai/free/en/authors/mostafa-abdou/)

[See all 38 people →](https://md.research.elamur.ai/free/en/countries/denmark/people/)

## Works in our library (79)

Works of its institutions, the most cited first.

1. [**Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter**Zeerak Waseem, Dirk Hovy*2016 · 2,158 citations*](https://md.research.elamur.ai/free/en/papers/waseem-2016-hateful-symbols-or-hateful-people/)
2. [**A Primer in BERTology: What We Know About How BERT Works**Anna Rogers, Olga Kovaleva, Anna Rumshisky*2020 · 2,127 citations*](https://md.research.elamur.ai/free/en/papers/rogers-2020-primer-bertology-what-we-know/)
3. [**Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization**Dave Van Veen, Cara Van Uden, Louis Blankemeier, et al.*2023 · 925 citations*](https://md.research.elamur.ai/free/en/papers/veen-2023-adapted-large-language-models-outperform/)
4. [**Are You a Racist or Am I Seeing Things? Annotator Influence on Hate Speech Detection on Twitter**Zeerak Waseem*2016 · 760 citations*](https://md.research.elamur.ai/free/en/papers/waseem-2016-are-you-racist-or-am/)
5. [**Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm**Bjarke Felbo, Alan Mislove, Anders Søgaard, et al.*2017 · 617 citations*](https://md.research.elamur.ai/free/en/papers/felbo-2017-millions-emoji-occurrences-learn-any/)
6. [**Deep multi-task learning with low level tasks supervised at lower layers**Anders Søgaard, Yoav Goldberg*2016 · 584 citations*](https://md.research.elamur.ai/free/en/papers/sogaard-2016-deep-multi-task-learning-low/)
7. [**The Social Impact of Natural Language Processing**Dirk Hovy, Shannon L. Spruit*2016 · 516 citations*](https://md.research.elamur.ai/free/en/papers/hovy-2016-social-impact-natural-language-processing/)
8. [**On the Limitations of Unsupervised Bilingual Dictionary Induction**Anders Søgaard, Sebastian Ruder, Ivan Vulić*2018 · 396 citations*](https://md.research.elamur.ai/free/en/papers/sogaard-2018-limitations-unsupervised-bilingual-dictionary-induction/)
9. [**JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages**Željko Agić, Ivan Vulić*2019 · 373 citations*](https://md.research.elamur.ai/free/en/papers/agic-2019-jw300-wide-coverage-parallel-corpus/)
10. [**Neural Unsupervised Domain Adaptation in NLP–-A Survey**Alan Ramponi, Barbara Plank*2020 · 334 citations*](https://md.research.elamur.ai/free/en/papers/ramponi-2020-neural-unsupervised-domain-adaptation-nlp/)
11. [**MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims**Isabelle Augenstein, Christina Lioma, Dongsheng Wang, et al.*2019 · 318 citations*](https://md.research.elamur.ai/free/en/papers/augenstein-2019-multifc-real-world-multi-domain/)
12. [**Identifying beneficial task relations for multi-task learning in deep neural networks**Joachim Bingel, Anders Søgaard*2017 · 305 citations*](https://md.research.elamur.ai/free/en/papers/bingel-2017-identifying-beneficial-task-relations-multi/)
13. [**SemEval-2019 Task 7: RumourEval, Determining Rumour Veracity and Support for Rumours**Genevieve Gorrell, Elena Kochkina, Maria Liakata, et al.*2019 · 290 citations*](https://md.research.elamur.ai/free/en/papers/gorrell-2019-semeval-2019-task-7-rumoureval/)
14. [**Challenges and Strategies in Cross-Cultural NLP**Daniel Hershcovich, Stella Frank, Heather Lent, et al.*2022 · 290 citations*](https://md.research.elamur.ai/free/en/papers/hershcovich-2022-challenges-strategies-cross-cultural-nlp/)
15. [**Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study**Yong Cao, Li Zhou, Seolhwa Lee, et al.*2023 · 278 citations*](https://md.research.elamur.ai/free/en/papers/cao-2023-assessing-cross-cultural-alignment-between/)
16. [**A Diagnostic Study of Explainability Techniques for Text Classification**Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, et al.*2020 · 273 citations*](https://md.research.elamur.ai/free/en/papers/atanasova-2020-diagnostic-study-explainability-techniques-text/)
17. [**LexGLUE: A Benchmark Dataset for Legal Language Understanding in English**Ilias Chalkidis; Abhik Jana; Dirk Hartung; Michael Bommarito; Ion Androutsopoulos; Daniel Martin Katz;, Nikolaos Aletras*2021 · 256 citations*](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-lexglue-benchmark-dataset-legal-language/)
18. [**Factuality Challenges in the Era of Large Language Models**Isabelle Augenstein, Timothy Baldwin, Meeyoung Cha, et al.*2023 · 241 citations*](https://md.research.elamur.ai/free/en/papers/augenstein-2023-factuality-challenges-era-large-language/)
19. [**Humanity's Last Exam**Long Phan, Alice Gatti, Ziwen Han, et al.*2025 · 235 citations*](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/)
20. [**Findings of the Third Shared Task on Multimodal Machine Translation**Loïc Barrault, Fethi Bougares, Lucia Specia, et al.*2018 · 227 citations*](https://md.research.elamur.ai/free/en/papers/barrault-2018-findings-third-shared-task-multimodal/)
21. [**Generating Fact Checking Explanations**Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, et al.*2020 · 219 citations*](https://md.research.elamur.ai/free/en/papers/atanasova-2020-generating-fact-checking-explanations/)
22. [**Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning**Shivalika Singh, Freddie Vargus, Daniel D'souza, et al.*2024 · 202 citations*](https://md.research.elamur.ai/free/en/papers/singh-2024-aya-dataset-open-access-collection/)
23. [**Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss**Barbara Plank, Anders Søgaard, Yoav Goldberg*2016 · 201 citations*](https://md.research.elamur.ai/free/en/papers/plank-2016-multilingual-part-speech-tagging-bidirectional/)
24. [**Multilingual Projection for Parsing Truly Low-Resource Languages**Željko Agić, Anders Johannsen, Barbara Plank, et al.*2016 · 195 citations*](https://md.research.elamur.ai/free/en/papers/agic-2016-multilingual-projection-parsing-truly-low/)
25. [**A Survey on Stance Detection for Mis- and Disinformation Identification**Momchil Hardalov, Arnav Arora, Preslav Nakov, et al.*2022 · 187 citations*](https://md.research.elamur.ai/free/en/papers/hardalov-2022-survey-stance-detection-mis-disinformation/)

[See all 79 works →](https://md.research.elamur.ai/free/en/countries/denmark/works/)

## Concepts, shelves and topics

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

💡 Concepts 2[Lexicography · 1 work](https://md.research.elamur.ai/free/en/concepts/lexicography/) · [Part-of-speech tagging · 1 work](https://md.research.elamur.ai/free/en/concepts/part-of-speech-tagging/)

📚 Shelves 13[Natural language processing · 45 works](https://md.research.elamur.ai/free/en/shelves/nlp/) · [Linguistics & languages · 45 works](https://md.research.elamur.ai/free/en/shelves/linguistics/) · [Law · 5 works](https://md.research.elamur.ai/free/en/shelves/law/) · [AI & machine learning · 4 works](https://md.research.elamur.ai/free/en/shelves/ai/) · [Machine translation · 12 works](https://md.research.elamur.ai/free/en/shelves/machine-translation/) · [English · 16 works](https://md.research.elamur.ai/free/en/shelves/en/) · [Mathematics & statistics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) · [Other · 1 work](https://md.research.elamur.ai/free/en/shelves/other/) · [Machine translation · 5 works](https://md.research.elamur.ai/free/en/shelves/mtrans/) · [Society & ethics · 1 work](https://md.research.elamur.ai/free/en/shelves/society/) · [Ancient Hebrew · 2 works](https://md.research.elamur.ai/free/en/shelves/hbo/) · [Aramaic · 1 work](https://md.research.elamur.ai/free/en/shelves/arc/) · [History & humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/history/)

🧭 Topics 27[Sentiment & emotion · 10 works](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Multilingual & cross-lingual NLP · 11 works](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Bias, fairness & safety · 3 works](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Evaluation & benchmarks · 7 works](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Summarization · 1 work](https://md.research.elamur.ai/free/en/topics/summarization/) · [Low-resource languages · 3 works](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · [Idioms & multiword expressions · 2 works](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) · [Language models & pretraining · 3 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Legal AI · 5 works](https://md.research.elamur.ai/free/en/topics/legal-ai/) · [Interpretability · 2 works](https://md.research.elamur.ai/free/en/topics/interpretability/) · [Machine translation · 4 works](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Discourse analysis · 4 works](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · [Part-of-speech tagging · 2 works](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) · [Morphology · 2 works](https://md.research.elamur.ai/free/en/topics/morphology/) · [Vision & language · 2 works](https://md.research.elamur.ai/free/en/topics/multimodal/)+12 more

## Works by year

### 2020s

[**2026** 1 work](https://md.research.elamur.ai/free/en/papers/zhang-2026-language-models-restoration-latin-legal/) · [**2025** 2 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2025/) · [**2024** 7 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2024/) · [**2023** 9 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2023/) · [**2022** 2 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2022/) · [**2021** 10 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2021/) · [**2020** 10 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2020/)

### 2010s

[**2019** 7 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2019/) · [**2018** 5 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2018/) · [**2017** 5 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2017/) · [**2016** 14 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2016/) · [**2014** 1 work](https://md.research.elamur.ai/free/en/papers/thomas-2014-negation-scope-spelling-variation-text/) · [**2013** 2 works](https://md.research.elamur.ai/free/en/countries/denmark/year/2013/)

### 2000s

[**2009** 1 work](https://md.research.elamur.ai/free/en/papers/jongejan-2009-automatic-training-lemmatization-rules-that/) · [**2006** 1 work](https://md.research.elamur.ai/free/en/papers/paggio-2006-annotating-information-structure-corpus-spoken/) · [**2001** 1 work](https://md.research.elamur.ai/free/en/papers/hardt-2001-generation-vp-ellipsis-corpus-based/)

### 1980s

[**1982** 1 work](https://md.research.elamur.ai/free/en/papers/maegaard-1982-transfer-finite-verb-forms-machine/)

- [← back to](https://md.research.elamur.ai/free/en/countries/) — countries

Updated 23 October 2026