---
title: "Belgium — research institutions, scientists and papers"
description: "Belgium: 6 institutions with papers in our library in 3 agglomerations, 26 people with a page, 47 works, 13,777 citations."
canonical: "https://research.elamur.ai/free/en/countries/belgium/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/belgium/)

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

# Belgium

Country 6 institutions in 3 agglomerations · [all countries](https://md.research.elamur.ai/free/en/countries/)

[**6** institutions with a page](https://md.research.elamur.ai/free/en/countries/belgium/#institutions) · [**3** agglomerations](https://md.research.elamur.ai/free/en/countries/belgium/#agglomerations) · [**26** people with a page](https://md.research.elamur.ai/free/en/countries/belgium/#authors) · [**47** works in our library](https://md.research.elamur.ai/free/en/countries/belgium/#works) · [**13,777** citations of their works](https://md.research.elamur.ai/free/en/countries/belgium/#works)

## About

### Profile

Belgium appears on this site through a compact group of research institutions: five universities and one government body. They sit in a handful of urban centres. [KU Leuven](https://md.research.elamur.ai/free/en/universities/ku-leuven/) is in Leuven, [Ghent University](https://md.research.elamur.ai/free/en/universities/ghent-university/) in [Ghent](https://md.research.elamur.ai/free/en/agglomerations/ghent/), and the [University of Antwerp](https://md.research.elamur.ai/free/en/universities/university-of-antwerp/) in [Antwerp](https://md.research.elamur.ai/free/en/agglomerations/antwerp/). [UCLouvain](https://md.research.elamur.ai/free/en/universities/uclouvain/) is based at Louvain-la-Neuve, which the library files under the [Brussels](https://md.research.elamur.ai/free/en/agglomerations/brussels/) agglomeration. Brussels also hosts the [Vrije Universiteit Brussel](https://md.research.elamur.ai/free/en/universities/vrije-universiteit-brussel/) and the [European Commission](https://md.research.elamur.ai/free/en/government/european-commission/), the one public institution in the group.

Among the works here, Belgian research is almost entirely about language. The largest field is linguistics and languages, followed by natural language processing and machine translation. A smaller strand belongs to history and the humanities, and single works touch AI and machine learning and mathematics and statistics. The picture covers only the papers and people on this site. It is a view of Belgian language science as this collection captures it, not a survey of the country's research.

KU Leuven contributes the most works and the most cited output among the Belgian institutions. UCLouvain and Ghent University follow at a distance. The University of Antwerp, the European Commission and the Vrije Universiteit Brussel each hold smaller sets of papers, though several of these are cited widely.

### History

The earliest Belgian works in our library come from the University of Antwerp and belong to the memory-based learning tradition. In 1996 [Walter Daelemans](https://md.research.elamur.ai/free/en/authors/walter-daelemans/) and colleagues presented [MBT](https://md.research.elamur.ai/free/en/papers/daelemans-1996-mbt-memory-based-part-speech/), a tagger-generator that learns part-of-speech tagging by storing tagged examples from a corpus. In 1999 [Erik Tjong Kim Sang](https://md.research.elamur.ai/free/en/authors/erik-tjong-kim-sang/) and Jorn Veenstra followed with [Representing Text Chunks](https://md.research.elamur.ai/free/en/papers/sang-1999-representing-text-chunks/), which compared different ways of encoding phrase chunks for machine learning.

The middle of the 2000s brought two new lines. One was syntactic representation: the 2006 paper on typed dependency parses, linked to both KU Leuven and UCLouvain, became the most cited Belgian work here. The other was multilingual resources from the European Commission. The same year saw the JRC-Acquis parallel corpus, and a translation memory followed in 2012. Antwerp's work then turned towards discourse-level and semantic problems: Dutch coreference in 2008, and the scope of hedge cues in biomedical texts in 2009 and 2010.

In the 2010s the centre of gravity shifted to Ghent and to Leuven and Louvain-la-Neuve. Ghent built a run of papers on sentiment and irony in social media between 2016 and 2018. UCLouvain produced work on readability in 2012 and on discourse markers in 2015 and 2017. KU Leuven added coreference in 2013 and lexical semantics in 2016.

From about 2020 the Belgian works follow the field's move towards pretrained language models, evaluation and annotation disagreement. RobBERT appeared in 2020, cross-cultural NLP and natural language inference work in 2022, and large benchmarks in 2025. A parallel line on ancient texts and semantic change runs from 2020 to 2026.

### Research profile

Sentiment and emotion form the largest topic among the Belgian works. They are concentrated at Ghent University. The most cited of these is [SemEval-2016 Task 5: Aspect Based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/), the report on the third round of the shared challenge in aspect-level sentiment analysis. Ghent researchers then turned to irony, which reverses the literal meaning of a message and so misleads sentiment systems. [Exploring the Realization of Irony in Twitter Data](https://md.research.elamur.ai/free/en/papers/hee-2016-exploring-realization-irony-twitter-data/) and the 2016 study of hashtagged ironic tweets built a hand-annotated English corpus. [We Usually Don't Like Going to the Dentist](https://md.research.elamur.ai/free/en/papers/hee-2018-we-usually-don-t-like/) used common-sense knowledge to spot the clash between a positive surface and a known bad situation. The line closes with a 2023 review of irony and sarcasm research, [The Iron(ic) Melting Pot](https://md.research.elamur.ai/free/en/papers/loakman-2023-iron-ic-melting-pot-reviewing/), which proposes an evaluation statement modelled on data statements.

[Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) and [multilingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) are anchored in Brussels by the European Commission's resources. [The JRC-Acquis](https://md.research.elamur.ai/free/en/papers/steinberger-2006-jrc-acquis-multilingual-aligned-parallel/) answered the lack of large parallel corpora that did not always pair a major language with others. The [DGT-TM](https://md.research.elamur.ai/free/en/papers/steinberger-2012-dgt-tm-freely-available-translation/) translation memory, released in 2011 and documented in 2012, extended the same effort. Both sit on the library's [machine translation shelf](https://md.research.elamur.ai/free/en/shelves/machine-translation/).

Syntax, tagging and parsing make up a third strand. Besides MBT and the chunking study from Antwerp, the dependency work of 2006 set out rules for turning Penn Treebank phrase-structure trees into typed dependencies. The topics here include [part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/), [dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) and [morphology](https://md.research.elamur.ai/free/en/topics/morphology/). [UniMorph 4.0](https://md.research.elamur.ai/free/en/papers/batsuren-2022-unimorph-4/) represents morphology. The VarDial 2018 report, [Language Identification and Morphosyntactic Tagging](https://md.research.elamur.ai/free/en/papers/zampieri-2018-language-identification-morphosyntactic-tagging-second/), linked to KU Leuven, covers shared tasks on closely related languages and dialects.

[Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) and [discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) run through several institutions. KU Leuven is associated with the sieve-based coreference system of 2013. Ghent University and the University of Antwerp share [A Coreference Corpus and Resolution System for Dutch](https://md.research.elamur.ai/free/en/papers/hendrickx-2008-coreference-corpus-resolution-system-dutch/), which supplied both annotated data and a system for a language that had lacked them. At UCLouvain, [Ludivine Crible](https://md.research.elamur.ai/free/en/authors/ludivine-crible/) asked whether one sense taxonomy could serve discourse markers in both speech and writing. The 2017 paper [Discourse Markers in Speech](https://md.research.elamur.ai/free/en/papers/crible-2017-discourse-markers-speech-distinctive-features/) showed how schemes built for planned writing fall short for spoken language.

A more recent group of works concerns [language models](https://md.research.elamur.ai/free/en/topics/language-models/), [evaluation and benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) and [reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/). KU Leuven is linked to [RobBERT](https://md.research.elamur.ai/free/en/papers/delobelle-2020-robbert-dutch-roberta-based-language/), a dedicated Dutch model built because multilingual models such as mBERT tended to trail single-language ones. It is also linked to [SimVerb-3500](https://md.research.elamur.ai/free/en/papers/gerz-2016-simverb-3500-large-scale-evaluation/), an evaluation set aimed at verbs rather than nouns. KU Leuven and the Vrije Universiteit Brussel share [Humanity's Last Exam](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/), a benchmark built because tests such as MMLU had become close to saturated. Ghent University is linked to DeepProbLog, which combines neural networks with probabilistic logic programming.

At UCLouvain, work on natural language inference examines why annotators disagree and how to tell genuine variation from error. The Belgian works also include a framework for cultural variation in NLP systems, event argument extraction by prompting, and a dynamically generated dataset for detecting online hate.

Finally, a humanities strand links language technology with old texts. The topics include [Hebrew and Aramaic](https://md.research.elamur.ai/free/en/topics/hebrew-aramaic/), [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/), [Latin](https://md.research.elamur.ai/free/en/topics/latin/) and [historical linguistics and language change](https://md.research.elamur.ai/free/en/topics/language-change/). UCLouvain is associated with a 2020 joint-learning approach to lemmatising and tagging three under-resourced ancient languages. [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/) belongs to this area, as does [Transparent Semantic Change Detection with Dependency-Based Profiles](https://md.research.elamur.ai/free/en/papers/tat-2026-transparent-semantic-change-detection-dependency/). That paper describes each target word by its syntactic dependencies, and its authors come from KU Leuven and partner institutions.

### Leading scientists

[Marie-Catherine de Marneffe](https://md.research.elamur.ai/free/en/authors/marie-catherine-de-marneffe/) of UCLouvain heads the Belgian authors on this site. De Marneffe is the first author, with Bill MacCartney and Christopher D. Manning, of the 2006 typed dependency paper. More recent work concerns disagreement in natural language inference, including [Investigating Reasons for Disagreement in Natural Language Inference](https://md.research.elamur.ai/free/en/papers/jiang-2022-investigating-reasons-disagreement-natural-language/) with Nan-Jiang Jiang. De Marneffe is also a co-author of VariErr NLI, which separates annotation errors from legitimate label variation.

[Marco Marelli](https://md.research.elamur.ai/free/en/authors/marco-marelli/) is connected to Ghent University. Marelli's papers here are few but are cited widely.

[Veronique Hoste](https://md.research.elamur.ai/free/en/authors/veronique-hoste/) is connected to Ghent University and also to the University of Antwerp. Hoste is a co-author of the Ghent irony series, from the 2016 corpus studies to [SemEval-2018 Task 3: Irony Detection in English Tweets](https://md.research.elamur.ai/free/en/papers/hee-2018-semeval-2018-task-3-irony/) and the common-sense approach of the same year.

Walter Daelemans of the University of Antwerp, also connected to the Vrije Universiteit Brussel, stands behind the memory-based line. That line includes MBT and, with [Roser Morante](https://md.research.elamur.ai/free/en/authors/roser-morante/), the 2009 paper [Learning the Scope of Hedge Cues in Biomedical Texts](https://md.research.elamur.ai/free/en/papers/morante-2009-learning-scope-hedge-cues-biomedical/). Its authors present it as the first system to learn hedge scope. Morante, Vincent Van Asch and Daelemans later wrote [Memory-Based Resolution of In-Sentence Scopes of Hedge Cues](https://md.research.elamur.ai/free/en/papers/morante-2010-memory-based-resolution-sentence-scopes/), a system entered in a closed-track competition.

[Orphee De Clercq](https://md.research.elamur.ai/free/en/authors/orphee-de-clercq/) is another Ghent University author, and the Ghent works on sentiment and irony form the setting for this name. Erik Tjong Kim Sang, at Antwerp, is the first author of the chunk-representation study.

[Bruno Pouliquen](https://md.research.elamur.ai/free/en/authors/bruno-pouliquen/) of the European Commission co-authored the JRC-Acquis corpus. [Els Lefever](https://md.research.elamur.ai/free/en/authors/els-lefever/) and [Cynthia Van Hee](https://md.research.elamur.ai/free/en/authors/cynthia-van-hee/) of Ghent University worked together on irony, with Van Hee as first author throughout the series. [Yves Peirsman](https://md.research.elamur.ai/free/en/authors/yves-peirsman/), at KU Leuven, is a co-author of [Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules](https://md.research.elamur.ai/free/en/papers/lee-2013-deterministic-coreference-resolution-based-entity/). [Ralf Steinberger](https://md.research.elamur.ai/free/en/authors/ralf-steinberger/) of the European Commission is first author of both the JRC-Acquis and DGT-TM papers.

[Thomas François](https://md.research.elamur.ai/free/en/authors/thomas-francois/), connected to KU Leuven and UCLouvain, wrote with Cédrick Fairon [An “AI readability” Formula for French as a Foreign Language](https://md.research.elamur.ai/free/en/papers/francois-2012-ai-readability-formula-french-as/). The model assigns texts to CEFR proficiency levels.

### Landmark works

The most cited Belgian work in our library is [Generating Typed Dependency Parses from Phrase Structure Parses](https://md.research.elamur.ai/free/en/papers/marneffe-2006-generating-typed-dependency-parses-phrase/). Its rule system converts constituency trees from the Stanford parser into labelled grammatical relations. Many later papers in the library build on it.

Second is the SemEval-2016 aspect-based sentiment report, which defined shared datasets and evaluation for opinions about specific aspects of entities. Third is the JRC-Acquis, a sentence-aligned corpus of EU legal texts covering many languages at once.

Next in citations come the 1999 chunking study and the 2013 sieve-based coreference system. The sieve paper shows that a modular, interpretable sequence of rules, applied from the most precise to the least, could compete in coreference. The 2018 irony detection task brought Ghent's annotated tweets to a wide community of participants. RobBERT gave Dutch its own RoBERTa-style model. MBT made memory-based learning practical for building taggers in new languages.

Other widely cited works include [Learning from the Worst](https://md.research.elamur.ai/free/en/papers/vidgen-2021-learning-worst-dynamically-generated-datasets/), which used human-and-model rounds to make hate speech classifiers more robust, and [Challenges and Strategies in Cross-Cultural NLP](https://md.research.elamur.ai/free/en/papers/hershcovich-2022-challenges-strategies-cross-cultural-nlp/). Two KU Leuven works also stand out: [PAIE](https://md.research.elamur.ai/free/en/papers/ma-2022-prompt-extraction-paie-prompting-argument/), which adapts prompt tuning to event argument extraction, and Humanity's Last Exam.

### Labs and units

The six member institutions are the units of Belgian research on this site. KU Leuven has the broadest spread. Its people include Peirsman, François, [Miryam de Lhoneux](https://md.research.elamur.ai/free/en/authors/miryam-de-lhoneux/), [Tim Van De Cruys](https://md.research.elamur.ai/free/en/authors/tim-van-de-cruys/), [Rodrigo Wilkens](https://md.research.elamur.ai/free/en/authors/rodrigo-wilkens/), [Geert Adriaens](https://md.research.elamur.ai/free/en/authors/geert-adriaens/), Crible and [Eibert Tigchelaar](https://md.research.elamur.ai/free/en/authors/eibert-tigchelaar/). Its works range from parsing and coreference to Dutch language models, benchmarks and the study of ancient Hebrew and Aramaic texts.

Ghent University's people include Hoste, Marelli, De Clercq, Lefever, Van Hee, [Lieve Macken](https://md.research.elamur.ai/free/en/authors/lieve-macken/), [Arda Tezcan](https://md.research.elamur.ai/free/en/authors/arda-tezcan/) and [Thomas Demeester](https://md.research.elamur.ai/free/en/authors/thomas-demeester/). Its works centre on sentiment and irony, with DeepProbLog as a branch into neuro-symbolic AI.

At the University of Antwerp, the research group CLiPS is named as the source of the 2010 hedge-scope system. Its people include Daelemans, Hoste, Tjong Kim Sang, Morante, [Iris Hendrickx](https://md.research.elamur.ai/free/en/authors/iris-hendrickx/), [Eduard Hovy](https://md.research.elamur.ai/free/en/authors/eduard-hovy/), [Dirk Hovy](https://md.research.elamur.ai/free/en/authors/dirk-hovy/) and [Antal van den Bosch](https://md.research.elamur.ai/free/en/authors/antal-van-den-bosch/).

UCLouvain brings together de Marneffe, François, Wilkens, Crible, [Barbara Plank](https://md.research.elamur.ai/free/en/authors/barbara-plank/) and [Sandrine Zufferey](https://md.research.elamur.ai/free/en/authors/sandrine-zufferey/). Its work spans inference, readability, discourse and ancient languages.

The European Commission's authors include Pouliquen, Steinberger, [Andreas Eisele](https://md.research.elamur.ai/free/en/authors/andreas-eisele/), [Marco Turchi](https://md.research.elamur.ai/free/en/authors/marco-turchi/), [Wajdi Zaghouani](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) and [Simon Hengchen](https://md.research.elamur.ai/free/en/authors/simon-hengchen/). The Vrije Universiteit Brussel is connected with Daelemans, [Mustafa Jarrar](https://md.research.elamur.ai/free/en/authors/mustafa-jarrar/) and [Jasabanta Patro](https://md.research.elamur.ai/free/en/authors/jasabanta-patro/).

### Collaborations

Several works tie Belgian institutions to one another. The 2006 dependency paper is credited to both KU Leuven and UCLouvain. Several researchers, among them François, Wilkens and Crible, appear at both institutions, which connects Leuven with Louvain-la-Neuve. The Dutch coreference corpus joins Ghent University and the University of Antwerp, and Hoste is connected to both. Humanity's Last Exam links KU Leuven with the Vrije Universiteit Brussel, and so does the 2026 semantic change paper, whose authors describe themselves as KU Leuven and partners. Daelemans links Antwerp with the Brussels university.

Co-authors outside the Belgian group appear throughout. De Marneffe's 2006 paper was written with MacCartney and Manning, and the 2022 inference study with Jiang. Crible worked with Zufferey on the unified taxonomy and with Maria-Josep Cuenca on spoken discourse markers. François wrote with Fairon. Steinberger's resources were produced with colleagues in the Commission's translation and research services. The large shared-task reports and benchmarks bring many outside authors into Belgian works. These include the VarDial campaign, the SemEval tasks and Humanity's Last Exam.

There are no companies among the Belgian institutions here. The link between academic research and the public sector runs instead through the European Commission's freely released corpora, which serve university machine translation research.

### Timeline

From 1996 to 1999, Belgian research on this site begins at the University of Antwerp, with memory-based part-of-speech tagging and the encoding of text chunks.

From 2006 to 2010, the dependency-parsing paper and the JRC-Acquis corpus appear in 2006. They are followed by Dutch coreference in 2008 and by work on hedge scope in biomedical texts in 2009 and 2010.

From 2012 to 2015, French readability modelling and the DGT-TM translation memory appear in 2012, sieve-based coreference in 2013, and a unified taxonomy for discourse markers in 2015.

From 2016 to 2018, Ghent leads with the aspect-based sentiment task and the irony studies, ending in the 2018 shared task. SimVerb-3500 appears in 2016, the discourse marker annotation work in 2017, and DeepProbLog and the VarDial campaign in 2018.

From 2020 to 2023, the focus moves to language models and annotation. This period brings RobBERT and ancient-language tagging in 2020, adversarial hate speech data in 2021, and a cluster of 2022 papers on culture, inference, event extraction and morphology. The irony review follows in 2023.

From 2024 to 2026, VariErr NLI and manuscript dating appear in 2024, Humanity's Last Exam in 2025, and dependency-based semantic change detection in 2026. Among the works here, they extend Belgian language research into evaluation and into the study of historical texts.

## Where

## Agglomerations (3)

1. [**Brussels**4 institutions*9,992 citations*](https://md.research.elamur.ai/free/en/agglomerations/brussels/)
2. [**Ghent**1 institution*2,565 citations*](https://md.research.elamur.ai/free/en/agglomerations/ghent/)
3. [**Antwerp**1 institution*1,220 citations*](https://md.research.elamur.ai/free/en/agglomerations/antwerp/)

## Institutions (6)

### 🎓 Universities (5)

1. **[KU Leuven](https://md.research.elamur.ai/free/en/universities/ku-leuven/)**University · [Leuven](https://md.research.elamur.ai/free/en/agglomerations/brussels/), Belgium*20 works · 5,325 citations*
2. **[Ghent University](https://md.research.elamur.ai/free/en/universities/ghent-university/)**University · [Ghent](https://md.research.elamur.ai/free/en/agglomerations/ghent/), Belgium*14 works · 2,565 citations*
3. **[University of Antwerp](https://md.research.elamur.ai/free/en/universities/university-of-antwerp/)**University · [Antwerp](https://md.research.elamur.ai/free/en/agglomerations/antwerp/), Belgium*5 works · 1,220 citations*
4. **[UCLouvain](https://md.research.elamur.ai/free/en/universities/uclouvain/)**University · [Louvain-la-Neuve](https://md.research.elamur.ai/free/en/agglomerations/brussels/), Belgium*10 works · 3,619 citations*
5. **[Vrije Universiteit Brussel](https://md.research.elamur.ai/free/en/universities/vrije-universiteit-brussel/)**University · [Brussels](https://md.research.elamur.ai/free/en/agglomerations/brussels/), Belgium*2 works · 236 citations*

### 🏛️ Government research bodies (1)

1. **[European Commission](https://md.research.elamur.ai/free/en/government/european-commission/)**Government body · [Brussels](https://md.research.elamur.ai/free/en/agglomerations/brussels/), Belgium*2 works · 812 citations*

## People (26)

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

1. [**Marie-Catherine de Marneffe**UCLouvain*25 papers here · 11,576 citations*](https://md.research.elamur.ai/free/en/authors/marie-catherine-de-marneffe/)
2. [**Marco Marelli**Ghent University*2 papers here · 3,329 citations*](https://md.research.elamur.ai/free/en/authors/marco-marelli/)
3. [**Veronique Hoste**Ghent University*7 papers here · 3,220 citations*](https://md.research.elamur.ai/free/en/authors/veronique-hoste/)
4. [**Walter Daelemans**University of Antwerp*5 papers here · 2,261 citations*](https://md.research.elamur.ai/free/en/authors/walter-daelemans/)
5. [**Orphee De Clercq**Ghent University*3 papers here · 1,901 citations*](https://md.research.elamur.ai/free/en/authors/orphee-de-clercq/)
6. [**Erik Tjong Kim Sang**University of Antwerp*3 papers here · 1,257 citations*](https://md.research.elamur.ai/free/en/authors/erik-tjong-kim-sang/)
7. [**Bruno Pouliquen**European Commission*2 papers here · 1,244 citations*](https://md.research.elamur.ai/free/en/authors/bruno-pouliquen/)
8. [**Els Lefever**Ghent University*5 papers here · 1,222 citations*](https://md.research.elamur.ai/free/en/authors/els-lefever/)
9. [**Cynthia Van Hee**Ghent University*4 papers here · 1,066 citations*](https://md.research.elamur.ai/free/en/authors/cynthia-van-hee/)
10. [**Yves Peirsman**KU Leuven*2 papers here · 1,042 citations*](https://md.research.elamur.ai/free/en/authors/yves-peirsman/)
11. [**Ralf Steinberger**European Commission*2 papers here · 878 citations*](https://md.research.elamur.ai/free/en/authors/ralf-steinberger/)
12. [**Thomas François**KU Leuven*4 papers here · 857 citations*](https://md.research.elamur.ai/free/en/authors/thomas-francois/)
13. [**Roser Morante**University of Antwerp*3 papers here · 781 citations*](https://md.research.elamur.ai/free/en/authors/roser-morante/)
14. [**Iris Hendrickx**University of Antwerp*2 papers here · 451 citations*](https://md.research.elamur.ai/free/en/authors/iris-hendrickx/)
15. [**Miryam de Lhoneux**KU Leuven*2 papers here · 333 citations*](https://md.research.elamur.ai/free/en/authors/miryam-de-lhoneux/)
16. [**Lieve Macken**Ghent University*2 papers here · 243 citations*](https://md.research.elamur.ai/free/en/authors/lieve-macken/)
17. [**Arda Tezcan**Ghent University*2 papers here · 241 citations*](https://md.research.elamur.ai/free/en/authors/arda-tezcan/)
18. [**Thomas Demeester**Ghent University*3 papers here · 226 citations*](https://md.research.elamur.ai/free/en/authors/thomas-demeester/)
19. [**Tim Van De Cruys**KU Leuven*3 papers here · 205 citations*](https://md.research.elamur.ai/free/en/authors/tim-van-de-cruys/)
20. [**Rodrigo Wilkens**KU Leuven*4 papers here · 120 citations*](https://md.research.elamur.ai/free/en/authors/rodrigo-wilkens/)
21. [**Ludivine Crible**KU Leuven*2 papers here · 70 citations*](https://md.research.elamur.ai/free/en/authors/ludivine-crible/)
22. [**Karel D'Oosterlinck**Ghent University*2 papers here · 69 citations*](https://md.research.elamur.ai/free/en/authors/karel-d-oosterlinck/)
23. [**Geert Adriaens**KU Leuven*2 papers here · 47 citations*](https://md.research.elamur.ai/free/en/authors/geert-adriaens/)
24. [**Eibert Tigchelaar**KU Leuven*2 papers here · 27 citations*](https://md.research.elamur.ai/free/en/authors/eibert-tigchelaar/)
25. [**Anne Breitbarth**Ghent University*2 papers here · 19 citations*](https://md.research.elamur.ai/free/en/authors/anne-breitbarth/)

[See all 26 people →](https://md.research.elamur.ai/free/en/countries/belgium/people/)

## Works in our library (47)

Works of its institutions, the most cited first.

1. [**Generating Typed Dependency Parses from Phrase Structure Parses**Marie-Catherine de Marneffe, Bill MacCartney, Christopher D. Manning*2006 · 2,886 citations*](https://md.research.elamur.ai/free/en/papers/marneffe-2006-generating-typed-dependency-parses-phrase/)
2. [**SemEval-2016 Task 5: Aspect Based Sentiment Analysis**Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, et al.*2016 · 1,656 citations*](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/)
3. [**The JRC-Acquis: A Multilingual Aligned Parallel Corpus with 20+ Languages**Ralf Steinberger, Bruno Pouliquen, Anna Widiger, et al.*2006 · 656 citations*](https://md.research.elamur.ai/free/en/papers/steinberger-2006-jrc-acquis-multilingual-aligned-parallel/)
4. [**Representing Text Chunks**Erik F. Tjong Kim Sang, Jorn Veenstra*1999 · 569 citations*](https://md.research.elamur.ai/free/en/papers/sang-1999-representing-text-chunks/)
5. [**Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules**Heeyoung Lee, Angel Chang, Yves Peirsman, et al.*2013 · 536 citations*](https://md.research.elamur.ai/free/en/papers/lee-2013-deterministic-coreference-resolution-based-entity/)
6. [**SemEval-2018 Task 3: Irony Detection in English Tweets**Cynthia Van Hee, Els Lefever, Véronique Hoste*2018 · 467 citations*](https://md.research.elamur.ai/free/en/papers/hee-2018-semeval-2018-task-3-irony/)
7. [**RobBERT: a Dutch RoBERTa-based Language Model**Pieter Delobelle, Thomas Winters, Bettina Berendt*2020 · 346 citations*](https://md.research.elamur.ai/free/en/papers/delobelle-2020-robbert-dutch-roberta-based-language/)
8. [**MBT: A Memory-Based Part of Speech Tagger-Generator**Walter Daelemans, Jakub Zavrel, Peter Berck, et al.*1996 · 336 citations*](https://md.research.elamur.ai/free/en/papers/daelemans-1996-mbt-memory-based-part-speech/)
9. [**Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection**Bertie Vidgen, Tristan Thrush, Zeerak Waseem, et al.*2021 · 320 citations*](https://md.research.elamur.ai/free/en/papers/vidgen-2021-learning-worst-dynamically-generated-datasets/)
10. [**SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity**Daniela Gerz, Ivan Vulić, Felix Hill, et al.*2016 · 315 citations*](https://md.research.elamur.ai/free/en/papers/gerz-2016-simverb-3500-large-scale-evaluation/)
11. [**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/)
12. [**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/)
13. [**Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction**Yubo Ma, Zehao Wang, Yixin Cao, et al.*2022 · 225 citations*](https://md.research.elamur.ai/free/en/papers/ma-2022-prompt-extraction-paie-prompting-argument/)
14. [**Learning the Scope of Hedge Cues in Biomedical Texts**Roser Morante, Walter Daelemans*2009 · 175 citations*](https://md.research.elamur.ai/free/en/papers/morante-2009-learning-scope-hedge-cues-biomedical/)
15. [**An “AI readability” Formula for French as a Foreign Language**Thomas François, Cédrick Fairon*2012 · 174 citations*](https://md.research.elamur.ai/free/en/papers/francois-2012-ai-readability-formula-french-as/)
16. [**Language Identification and Morphosyntactic Tagging: The Second VarDial Evaluation Campaign**Marcos Zampieri, Shervin Malmasi, Preslav Nakov, et al.*2018 · 169 citations*](https://md.research.elamur.ai/free/en/papers/zampieri-2018-language-identification-morphosyntactic-tagging-second/)
17. [**DeepProbLog: Neural Probabilistic Logic Programming**Robin Manhaeve, Sebastijan Dumančić, Angelika Kimmig, et al.*2018 · 166 citations*](https://md.research.elamur.ai/free/en/papers/manhaeve-2018-deepproblog-neural-probabilistic-logic/)
18. [**DGT-TM: A freely available Translation Memory in 22 languages**Ralf Steinberger, Andreas Eisele, Szymon Klocek, et al.*2012 · 156 citations*](https://md.research.elamur.ai/free/en/papers/steinberger-2012-dgt-tm-freely-available-translation/)
19. [**Investigating Reasons for Disagreement in Natural Language Inference**Nan-Jiang Jiang, Marie-Catherine de Marneffe*2022 · 104 citations*](https://md.research.elamur.ai/free/en/papers/jiang-2022-investigating-reasons-disagreement-natural-language/)
20. [**A Coreference Corpus and Resolution System for Dutch**Iris Hendrickx, Gosse Bouma, Frederik Coppens, et al.*2008 · 92 citations*](https://md.research.elamur.ai/free/en/papers/hendrickx-2008-coreference-corpus-resolution-system-dutch/)
21. [**UniMorph 4.0: Universal Morphology**Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa*2022 · 82 citations*](https://md.research.elamur.ai/free/en/papers/batsuren-2022-unimorph-4/)
22. [**Monday mornings are my fave :) #not Exploring the Automatic Recognition of Irony in English tweets**Cynthia Van Hee, Els Lefever, Véronique Hoste*2016 · 59 citations*](https://md.research.elamur.ai/free/en/papers/hee-2016-monday-mornings-are-my-fave/)
23. [**Discourse Markers in Speech: Distinctive Features and Corpus Annotation**Ludivine Crible, Maria-Josep Cuenca*2017 · 53 citations*](https://md.research.elamur.ai/free/en/papers/crible-2017-discourse-markers-speech-distinctive-features/)
24. [**VariErr NLI: Separating Annotation Error from Human Label Variation**Leon Weber-Genzel, Siyao Peng, Marie-Catherine De Marneffe, et al.*2024 · 51 citations*](https://md.research.elamur.ai/free/en/papers/genzel-2024-varierr-nli-separating-annotation-error/)
25. [**Exploring the Realization of Irony in Twitter Data**Cynthia Van Hee, Els Lefever, Véronique Hoste*2016 · 48 citations*](https://md.research.elamur.ai/free/en/papers/hee-2016-exploring-realization-irony-twitter-data/)

[See all 47 works →](https://md.research.elamur.ai/free/en/countries/belgium/works/)

## Concepts, shelves and topics

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

💡 Concepts 4[Coreference resolution · 1 work](https://md.research.elamur.ai/free/en/concepts/coreference-resolution/) · [Part-of-speech tagging · 1 work](https://md.research.elamur.ai/free/en/concepts/part-of-speech-tagging/) · [Knowledge representation and reasoning · 1 work](https://md.research.elamur.ai/free/en/concepts/knowledge-representation/) · [Implicature · 1 work](https://md.research.elamur.ai/free/en/concepts/implicature/)

📚 Shelves 20[Computer Science · 39 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 38 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 20 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Arts and Humanities · 22 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Psychology · 5 works](https://md.research.elamur.ai/free/en/shelves/psychology/) · [Experimental and Cognitive Psychology · 1 work](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · [Computer Vision and Pattern Recognition · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Sociology and Political Science · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · [Literature and Literary Theory · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/literature-and-literary-theory/) · [Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) · [Biochemistry, Genetics and Molecular Biology · 1 work](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · [Molecular Biology · 1 work](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · [Developmental and Educational Psychology · 3 works](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · [History · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/history/)+5 more

🧭 Topics 24[Sentiment & emotion · 6 works](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [English · 11 works](https://md.research.elamur.ai/free/en/topics/english/) · [Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Coreference resolution · 2 works](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · [Part-of-speech tagging · 3 works](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) · [French · 4 works](https://md.research.elamur.ai/free/en/topics/french/) · [Reasoning · 3 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Machine translation · 6 works](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Dependency parsing · 1 work](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) · [Syntax & grammar formalisms · 1 work](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) · [Multilingual & cross-lingual NLP · 2 works](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Discourse analysis · 3 works](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · [Morphology · 3 works](https://md.research.elamur.ai/free/en/topics/morphology/) · [Hebrew & Aramaic · 5 works](https://md.research.elamur.ai/free/en/topics/hebrew-aramaic/) · [Biblical Hebrew · 3 works](https://md.research.elamur.ai/free/en/topics/biblical-hebrew/)+9 more

## Works by year

### 2020s

[**2026** 8 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2026/) · [**2025** 1 work](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/) · [**2024** 3 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2024/) · [**2023** 2 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2023/) · [**2022** 5 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2022/) · [**2021** 1 work](https://md.research.elamur.ai/free/en/papers/vidgen-2021-learning-worst-dynamically-generated-datasets/) · [**2020** 3 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2020/)

### 2010s

[**2019** 2 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2019/) · [**2018** 4 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2018/) · [**2017** 1 work](https://md.research.elamur.ai/free/en/papers/crible-2017-discourse-markers-speech-distinctive-features/) · [**2016** 5 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2016/) · [**2015** 1 work](https://md.research.elamur.ai/free/en/papers/crible-2015-unified-taxonomy-annotate-discourse-markers/) · [**2013** 1 work](https://md.research.elamur.ai/free/en/papers/lee-2013-deterministic-coreference-resolution-based-entity/) · [**2012** 2 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2012/) · [**2010** 1 work](https://md.research.elamur.ai/free/en/papers/morante-2010-memory-based-resolution-sentence-scopes/)

### 2000s

[**2009** 1 work](https://md.research.elamur.ai/free/en/papers/morante-2009-learning-scope-hedge-cues-biomedical/) · [**2008** 1 work](https://md.research.elamur.ai/free/en/papers/hendrickx-2008-coreference-corpus-resolution-system-dutch/) · [**2006** 2 works](https://md.research.elamur.ai/free/en/countries/belgium/year/2006/)

### 1990s

[**1999** 1 work](https://md.research.elamur.ai/free/en/papers/sang-1999-representing-text-chunks/) · [**1996** 1 work](https://md.research.elamur.ai/free/en/papers/daelemans-1996-mbt-memory-based-part-speech/) · [**1994** 1 work](https://md.research.elamur.ai/free/en/papers/adriaens-1994-simplified-english-grammar-style-correction/)

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

Updated 23 October 2026