---
title: "Norway — research institutions, scientists and papers"
description: "Norway: 6 institutions with papers in our library in 4 agglomerations, 18 people with a page, 48 works, 6,445 citations."
canonical: "https://research.elamur.ai/free/en/countries/norway/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/norway/)

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

# Norway

Country 6 institutions in 4 agglomerations · [all countries](https://md.research.elamur.ai/free/en/countries/)

[**6** institutions with a page](https://md.research.elamur.ai/free/en/countries/norway/#institutions) · [**4** agglomerations](https://md.research.elamur.ai/free/en/countries/norway/#agglomerations) · [**18** people with a page](https://md.research.elamur.ai/free/en/countries/norway/#authors) · [**48** works in our library](https://md.research.elamur.ai/free/en/countries/norway/#works) · [**6,445** citations of their works](https://md.research.elamur.ai/free/en/countries/norway/#works)

## About

### Profile

Norway appears on this site through a group of universities whose researchers have contributed papers to the library. All of them are classified as universities, and they sit in four cities: [Oslo](https://md.research.elamur.ai/free/en/agglomerations/oslo/), [Trondheim](https://md.research.elamur.ai/free/en/agglomerations/trondheim/), [Bergen](https://md.research.elamur.ai/free/en/agglomerations/bergen/) and [Tromsø](https://md.research.elamur.ai/free/en/agglomerations/tromso/). Oslo is home to two of them, the [University of Oslo](https://md.research.elamur.ai/free/en/universities/university-of-oslo/) and [Fjellhaug Internasjonale Høgskole](https://md.research.elamur.ai/free/en/universities/fjellhaug-internasjonale-hogskole/). Trondheim is represented by the [Norwegian University of Science and Technology](https://md.research.elamur.ai/free/en/universities/norwegian-university-of-science-and-technology/), Tromsø by [UiT The Arctic University of Norway](https://md.research.elamur.ai/free/en/universities/uit-the-arctic-university-of-norway/), and Bergen by the [University of Bergen](https://md.research.elamur.ai/free/en/universities/university-of-bergen/).

Among the works here, Norwegian research is overwhelmingly about language. Most papers belong to [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/), and a substantial share also fall under [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/). Smaller groups appear under [Machine translation](https://md.research.elamur.ai/free/en/shelves/machine-translation/) and, in a single recent case, [Life sciences & medicine](https://md.research.elamur.ai/free/en/shelves/life-sciences/). This reflects the selection of papers in our library rather than the full range of Norwegian science, which the library does not attempt to cover.

The University of Oslo is the centre of gravity. It contributes the largest group of works, and its papers have drawn by far the most attention. The Trondheim, Bergen and Tromsø universities each contribute a small set of papers, several of which are widely cited. Fjellhaug Internasjonale Høgskole contributes a distinct cluster of studies on the Hebrew Bible, which have so far been cited only rarely.

### History

The earliest Norwegian work in our library dates from 1997. In that year Kaja Borthen and Thorstein Fretheim, working in Trondheim, studied how sentential pronouns direct a listener's attention in English and Norwegian. They used a listening test with Norwegian participants to see how readers resolve the pronoun "det" when it carries no accent. That paper belongs to pragmatics and discourse rather than to computing, and it marks a theoretical strand that reappears later in the Norwegian works.

The early 2000s brought grammar engineering. [The Parallel Grammar Project](https://md.research.elamur.ai/free/en/papers/butt-2002-parallel-grammar-project/) of 2002, with [Helge Dyvik](https://md.research.elamur.ai/free/en/authors/helge-dyvik/) of Bergen among its authors, describes building comparable grammars for several languages in Lexical-Functional Grammar with the XLE parser. Two years later the English Resource Grammar was tested at scale against the British National Corpus. In 2006 [Stephan Oepen](https://md.research.elamur.ai/free/en/authors/stephan-oepen/) and Jan Tore Lønning set out a method for building corpora annotated with meaning representations. These works tie Oslo and Bergen to a line of research on precise, rule-based grammars and their evaluation.

Through the 2010s the Oslo work widened. Distributional semantics appears in 2010, studies of sentence splitting and tokenization in 2012, and coreference evaluation in 2013. From 2016 onward the output grows denser and more varied: large parallel corpora, discourse parsing, multiword expressions in treebanks, hate-speech detection, multilingual dependency parsing, and surveys of semantic change. The 2020s add transformer adaptation, shared tasks on social-media sentiment and memes, named entity recognition for African languages, interpretable word senses, and a massive multilingual dataset. Running alongside this, from 2012 to 2026, is the Fjellhaug series on digital study of biblical Hebrew.

### Research profile

The largest topic grouping among Norwegian works is [Hebrew & Aramaic](https://md.research.elamur.ai/free/en/topics/hebrew-aramaic/), closely tied to [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/). Almost all of it comes from Fjellhaug Internasjonale Høgskole. [Stones on Display in Joshua 6](https://md.research.elamur.ai/free/en/papers/winther-nielsen-2012-stones-display-joshua-6-linguistic/) proposes interactive tools for analysing the biblical text in place of static descriptions. [The Corpus as Tutor](https://md.research.elamur.ai/free/en/papers/winther-nielsen-2017-corpus-tutor-data-driven-persuasive/) presents learning software that builds Hebrew exercises straight from an annotated corpus. [Interfacing the Hebrew Bible](https://md.research.elamur.ai/free/en/papers/winther-nielsen-2019-interfacing-hebrew-bible-past-present/) discusses Bible Online Learner, which trains students on forms drawn from the text itself. Related pieces cover participant tracking in Exodus, an image database of biblical places and customs, and the dating of Biblical Hebrew. [Identifying Phrase Boundaries in the Samaritan Pentateuch](https://md.research.elamur.ai/free/en/papers/cantanhede-2026-identifying-phrase-boundaries-samaritan-pentateuch/) brings machine learning to the same textual tradition.

[Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) is a second strong thread, mostly from Oslo. [Parser Evaluation over Local and Non-Local Deep Dependencies](https://md.research.elamur.ai/free/en/papers/bender-2011-parser-evaluation-over-local-non/) asks how well parsers capture the relations needed for interpretation. [The 2018 Shared Task on Extrinsic Parser Evaluation](https://md.research.elamur.ai/free/en/papers/fares-2018-2018-shared-task-extrinsic-parser/) measures parsers by their usefulness in downstream applications. [Critical Reflections on Evaluation Practices in Coreference Resolution](https://md.research.elamur.ai/free/en/papers/holen-2013-critical-reflections-evaluation-practices-coreference/) questions how [coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) systems are scored.

Parsing and grammar form a closely connected group. Work on [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/), [dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) and [treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/) includes the CoNLL 2017 shared task associated with Tromsø and the Bergen study of how [multiword expressions](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) should be marked in treebanks. [Syntax & grammar formalisms](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) is represented by the ParGram project and by the grammar-based semantic annotation from Oslo. Basic preprocessing gets its own attention under [tokenization](https://md.research.elamur.ai/free/en/topics/tokenization/): [Tokenization: Returning to a Long Solved Problem](https://md.research.elamur.ai/free/en/papers/dridan-2012-tokenization-returning-long-solved-problem/) and the companion study of sentence boundary detection both show that steps often treated as settled still affect later results.

Meaning and its change over time make up another cluster, under [Historical linguistics & language change](https://md.research.elamur.ai/free/en/topics/language-change/) and [Lexical semantics & word embeddings](https://md.research.elamur.ai/free/en/topics/lexical-semantics/). The 2018 survey of diachronic embeddings, the 2010 regression model of adjective-noun composition and the 2023 study of definition generation all belong here. The last of these also touches [word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/). Theoretical semantics and pragmatics appear in [The lexical pragmatics of count-mass polysemy](https://md.research.elamur.ai/free/en/papers/falkum-2017-lexical-pragmatics-count-mass-polysemy/) and in the 2016 Tromsø study showing that anticausative verbs behave differently in Norwegian and English.

[Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) links the subtitle corpora from Oslo, the CoNLL 2017 parsing task, the African-language [named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) resource from the Bergen group of works, and the 2025 HPLT dataset. [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) is covered mainly by the Trondheim shared tasks on code-mixed tweets and Internet memes. Smaller topics include [discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/), [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [language models](https://md.research.elamur.ai/free/en/topics/language-models/) and [low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/).

### Leading scientists

[Mario Giulianelli](https://md.research.elamur.ai/free/en/authors/mario-giulianelli/) of the University of Oslo heads the list of people. Among the works here, Giulianelli is first author of [Interpretable Word Sense Representations via Definition Generation](https://md.research.elamur.ai/free/en/papers/giulianelli-2023-definition-generation-senses/), which represents word senses through generated dictionary-style definitions and applies them to the study of semantic change.

[Francis Tyers](https://md.research.elamur.ai/free/en/authors/francis-tyers/) is the researcher connected to UiT The Arctic University of Norway. The Tromsø works include [CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies](https://md.research.elamur.ai/free/en/papers/zeman-2017-conll-2017-shared-task-multilingual/), which required systems to parse plain text in many languages without gold-standard segmentation or tags.

Stephan Oepen of the University of Oslo appears on more Norwegian papers here than anyone else. Oepen's work runs from semantically annotated corpora and grammar evaluation in the 2000s, through tokenization and parser evaluation in the 2010s, to discourse parsing and meaning representation graphs. [DRS at MRP 2020](https://md.research.elamur.ai/free/en/papers/abzianidze-2020-drs-mrp-2020-dressing-up/) recasts Discourse Representation Structures as graphs for a shared parsing task.

[Pierre Lison](https://md.research.elamur.ai/free/en/authors/pierre-lison/), also in Oslo, is the first author of both OpenSubtitles corpus papers, the most cited Norwegian works in our library. Lison's work here is about assembling and aligning very large parallel corpora from film and television subtitles.

[Lilja Øvrelid](https://md.research.elamur.ai/free/en/authors/lilja-ovrelid/) of the University of Oslo co-authored the diachronic embeddings survey and the 2018 shared task on extrinsic parser evaluation. Øvrelid's work spans both syntactic analysis and lexical semantics.

[Bjorn Gamback](https://md.research.elamur.ai/free/en/authors/bjorn-gamback/) represents the Norwegian University of Science and Technology. Gambäck is first author of the Trondheim paper on classifying hate speech with convolutional neural networks, and the Trondheim people also include co-organisers of the SemEval-2020 sentiment and meme tasks, such as [Amitava Das](https://md.research.elamur.ai/free/en/authors/amitava-das/), [Partha Pakray](https://md.research.elamur.ai/free/en/authors/partha-pakray/) and [Alexander Gelbukh](https://md.research.elamur.ai/free/en/authors/alexander-gelbukh/).

[Erik Velldal](https://md.research.elamur.ai/free/en/authors/erik-velldal/) is another Oslo researcher with several papers here, working within the same language technology group as Oepen and Øvrelid.

[Andrey Kutuzov](https://md.research.elamur.ai/free/en/authors/andrey-kutuzov/) is first author of the survey on diachronic word embeddings, which frames the task of detecting words whose meaning shifts across time-sliced corpora.

[Vinit Ravishankar](https://md.research.elamur.ai/free/en/authors/vinit-ravishankar/) of Oslo co-authored [What can we learn from Semantic Tagging?](https://md.research.elamur.ai/free/en/papers/abdou-2018-what-can-we-learn-semantic/), which looks at what semantic tag prediction can contribute to other language tasks.

Helge Dyvik of the University of Bergen is a co-author of The Parallel Grammar Project. Bergen's people also include [Victoria Rosén](https://md.research.elamur.ai/free/en/authors/victoria-rosen/), first author of the guidelines on multiword expressions in treebanks, and [Murhaf Fares](https://md.research.elamur.ai/free/en/authors/murhaf-fares/), first author of the 2018 extrinsic parser evaluation task.

[Jonathon Read](https://md.research.elamur.ai/free/en/authors/jonathon-read/) of Oslo led the study of sentence boundary detection and co-authored the OPT discourse parsing system. [Dag Haug](https://md.research.elamur.ai/free/en/authors/dag-haug/) completes the first group of Oslo people shown for the country.

### Landmark works

The most cited Norwegian work in our library is [OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles](https://md.research.elamur.ai/free/en/papers/lison-2016-opensubtitles2016-extracting-large-parallel-corpora/) by Pierre Lison and Jörg Tiedemann. It presents a much larger and cleaner release of a multilingual subtitle collection and tests it in translation experiments. Its follow-up, [OpenSubtitles2018](https://md.research.elamur.ai/free/en/papers/lison-2018-opensubtitles2018-statistical-rescoring-sentence-alignments/), rebuilds the corpus from a complete database dump and adds statistical rescoring of sentence alignments to deal with noise.

Second is [AdapterHub: A Framework for Adapting Transformers](https://md.research.elamur.ai/free/en/papers/pfeiffer-2020-adapterhub-framework-adapting-transformers/). It starts from the cost of fine-tuning a full copy of a large pretrained model for every new task and offers a framework for small, shareable adapter modules instead.

Third is [Using Convolutional Neural Networks to Classify Hate-Speech](https://md.research.elamur.ai/free/en/papers/gamback-2017-convolutional-neural-networks-classify-hate/) from Trondheim, which applies convolutional networks to detecting hate speech on Twitter. The CoNLL 2017 shared task follows, then The Parallel Grammar Project, which compares grammars across languages within one formalism.

Further down the list come [Diachronic word embeddings and semantic shifts: a survey](https://md.research.elamur.ai/free/en/papers/kutuzov-2018-diachronic-word-embeddings-semantic-shifts/), and the two Trondheim-linked SemEval overviews: [SemEval-2020 Task 8: Memotion Analysis](https://md.research.elamur.ai/free/en/papers/sharma-2020-semeval-2020-task-8-memotion/), which made meme understanding a benchmark by combining image and text, and [SemEval-2020 Task 9](https://md.research.elamur.ai/free/en/papers/patwa-2020-semeval-2020-task-9-overview/), on sentiment in tweets that switch between languages, such as Hinglish.

Other much-cited works include [A Regression Model of Adjective-Noun Compositionality](https://md.research.elamur.ai/free/en/papers/guevara-2010-regression-model-adjective-noun-compositionality/), which learns how vectors for phrases can be built from their parts; [Discriminant-Based MRS Banking](https://md.research.elamur.ai/free/en/papers/oepen-2006-discriminant-based-mrs-banking/), on pairing each corpus sentence with a meaning representation; and [MasakhaNER 2.0](https://md.research.elamur.ai/free/en/papers/adelani-2022-masakhaner-2-0-africa-centric/), a human-annotated news corpus for entity recognition in Sub-Saharan African languages. [Road-testing the English Resource Grammar](https://md.research.elamur.ai/free/en/papers/baldwin-2004-road-testing-english-resource-grammar/) examined by hand why sentences failed to parse, and [Sentence Boundary Detection: A Long Solved Problem?](https://md.research.elamur.ai/free/en/papers/read-2012-sentence-boundary-detection-long-solved/) showed that published results for English were hard to compare.

### Labs and units

The member institutions differ clearly in what they bring. The University of Oslo carries most of the computational work: corpora, grammar-based semantics, parsing and its evaluation, distributional and diachronic semantics, and discourse processing. Its people form the largest group in the country.

The Norwegian University of Science and Technology combines an early pragmatics paper with later work on social media: hate speech, code-mixed sentiment and multimodal memes. Its people include Gambäck, [Erwin Marsi](https://md.research.elamur.ai/free/en/authors/erwin-marsi/), [Lars Bungum](https://md.research.elamur.ai/free/en/authors/lars-bungum/) and [Salman Khan](https://md.research.elamur.ai/free/en/authors/salman-khan/).

UiT The Arctic University of Norway contributes multilingual parsing, a psycholinguistic study of anticausatives, and a 2026 paper on [evaluating multilingual text simplification](https://md.research.elamur.ai/free/en/papers/pelloni-2026-evaluation-multilingual-text-simplification-mental/) for mental health material in languages other than English.

The University of Bergen is linked to grammar engineering, multiword expressions and African-language named entity recognition. Its people also include [Jacopo Romoli](https://md.research.elamur.ai/free/en/authors/jacopo-romoli/). Fjellhaug Internasjonale Høgskole, with [Christian Canu Højgaard](https://md.research.elamur.ai/free/en/authors/christian-canu-hojgaard/) among its people, is devoted to computational and pedagogical study of the Hebrew Bible.

### Collaborations

Many of the most cited Norwegian works are large joint efforts. The CoNLL 2017 and SemEval-2020 tasks, MasakhaNER 2.0, AdapterHub and the HPLT dataset all have long author lists, so Norwegian researchers often appear as one partner among many. [An Expanded Massive Multilingual Dataset for High-Performance Language Technologies](https://md.research.elamur.ai/free/en/papers/burchell-2025-expanded-massive-multilingual-dataset-high/) is a recent example of this kind of shared infrastructure work.

Some partnerships are visible in the titles themselves. [OPT: Oslo–Potsdam–Teesside](https://md.research.elamur.ai/free/en/papers/oepen-2016-opt-oslo-potsdam-teesside-pipelining/) names its Oslo, Potsdam and Teesside contributors in a system that combines rules, rankers and classifier ensembles for shallow discourse parsing. The grammar evaluation papers of 2004 and 2011 bring Oepen together with Emily M. Bender, Dan Flickinger and Timothy Baldwin. Within Norway, Fares connects Bergen and Oslo through the extrinsic parser evaluation task, co-authored with Oepen and Øvrelid. The Trondheim SemEval work links NTNU people with co-organisers such as Das, Pakray and Gelbukh.

### Timeline

The late 1990s and the 2000s are thinly represented. The 1997 Trondheim study of pronouns and attention comes first, followed by the ParGram project in 2002, the grammar road test in 2004 and the MRS banking method in 2006. Grammar formalisms and their evaluation dominate this period.

From 2010 to 2013 the Oslo work turns to distributional semantics, deep dependency evaluation, tokenization, sentence splitting and coreference scoring, while the Fjellhaug series on Joshua 6 begins in 2012.

From 2016 to 2019 the output peaks. The OpenSubtitles corpora appear in 2016 and 2018; the OPT system, the multiword expression guidelines and the anticausative study in 2016; hate-speech detection, the CoNLL parsing task and the count-mass polysemy paper in 2017; and the diachronic survey, the extrinsic parser task and semantic tagging work in 2018. Fjellhaug publishes its corpus-driven learning and visualization papers in 2016, 2017 and 2019.

From 2020 onward the Norwegian works shift toward large models and multilingual resources: AdapterHub, the SemEval-2020 tasks and the DRS graph work in 2020, MasakhaNER 2.0 in 2022, definition-based word senses in 2023, the HPLT dataset in 2025, and in 2026 both mental-health text simplification and phrase boundaries in the Samaritan Pentateuch.

## Where

## Agglomerations (4)

1. [**Oslo**3 institutions*4,069 citations*](https://md.research.elamur.ai/free/en/agglomerations/oslo/)
2. [**Trondheim**1 institution*1,170 citations*](https://md.research.elamur.ai/free/en/agglomerations/trondheim/)
3. [**Bergen**1 institution*561 citations*](https://md.research.elamur.ai/free/en/agglomerations/bergen/)
4. [**Tromsø**1 institution*645 citations*](https://md.research.elamur.ai/free/en/agglomerations/tromso/)

## Institutions (6)

### 🎓 Universities (5)

1. **[University of Oslo](https://md.research.elamur.ai/free/en/universities/university-of-oslo/)**University · [Oslo](https://md.research.elamur.ai/free/en/agglomerations/oslo/), Norway*29 works · 3,700 citations*
2. **[Norwegian University of Science and Technology](https://md.research.elamur.ai/free/en/universities/norwegian-university-of-science-and-technology/)**University · [Trondheim](https://md.research.elamur.ai/free/en/agglomerations/trondheim/), Norway*5 works · 1,170 citations*
3. **[University of Bergen](https://md.research.elamur.ai/free/en/universities/university-of-bergen/)**University · [Bergen](https://md.research.elamur.ai/free/en/agglomerations/bergen/), Norway*3 works · 561 citations*
4. **[UiT The Arctic University of Norway](https://md.research.elamur.ai/free/en/universities/uit-the-arctic-university-of-norway/)**University · [Tromsø](https://md.research.elamur.ai/free/en/agglomerations/tromso/), Norway*3 works · 645 citations*
5. **[Fjellhaug Internasjonale Høgskole](https://md.research.elamur.ai/free/en/universities/fjellhaug-internasjonale-hogskole/)**University · [Oslo](https://md.research.elamur.ai/free/en/agglomerations/oslo/), Norway*8 works · 5 citations*

### 🤝 Nonprofits (1)

1. **[Norwegian Computing Center](https://md.research.elamur.ai/free/en/ngos/norwegian-computing-center/)**Nonprofit · [Oslo](https://md.research.elamur.ai/free/en/agglomerations/oslo/), Norway*2 works · 364 citations*

## People (18)

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

1. [**Francis Tyers**UiT The Arctic University of Norway*13 papers here · 1,863 citations*](https://md.research.elamur.ai/free/en/authors/francis-tyers/)
2. [**Stephan Oepen**University of Oslo*16 papers here · 1,529 citations*](https://md.research.elamur.ai/free/en/authors/stephan-oepen/)
3. [**Pierre Lison**University of Oslo*3 papers here · 1,465 citations*](https://md.research.elamur.ai/free/en/authors/pierre-lison/)
4. [**Lilja Øvrelid**University of Oslo*8 papers here · 1,333 citations*](https://md.research.elamur.ai/free/en/authors/lilja-ovrelid/)
5. [**Bjorn Gamback**Norwegian University of Science and Technology*4 papers here · 1,292 citations*](https://md.research.elamur.ai/free/en/authors/bjorn-gamback/)
6. [**Erik Velldal**University of Oslo*6 papers here · 916 citations*](https://md.research.elamur.ai/free/en/authors/erik-velldal/)
7. [**Andrey Kutuzov**University of Oslo*2 papers here · 611 citations*](https://md.research.elamur.ai/free/en/authors/andrey-kutuzov/)
8. [**Vinit Ravishankar**University of Oslo*2 papers here · 472 citations*](https://md.research.elamur.ai/free/en/authors/vinit-ravishankar/)
9. [**Helge Dyvik**University of Bergen*3 papers here · 457 citations*](https://md.research.elamur.ai/free/en/authors/helge-dyvik/)
10. [**Milen Kouylekov**University of Oslo*3 papers here · 439 citations*](https://md.research.elamur.ai/free/en/authors/milen-kouylekov/)
11. [**Ildikó Pilán**Norwegian Computing Center*2 papers here · 392 citations*](https://md.research.elamur.ai/free/en/authors/ildiko-pilan/)
12. [**Jonathon Read**University of Oslo*2 papers here · 373 citations*](https://md.research.elamur.ai/free/en/authors/jonathon-read/)
13. [**Dag Haug**University of Oslo*2 papers here · 305 citations*](https://md.research.elamur.ai/free/en/authors/dag-haug/)
14. [**Jan Tore Lønning**University of Oslo*3 papers here · 224 citations*](https://md.research.elamur.ai/free/en/authors/jan-tore-lonning/)
15. [**Rebecca Dridan**University of Oslo*2 papers here · 137 citations*](https://md.research.elamur.ai/free/en/authors/rebecca-dridan/)
16. [**Nikolay Arefyev**University of Oslo*3 papers here · 116 citations*](https://md.research.elamur.ai/free/en/authors/nikolay-arefyev/)
17. [**Victoria Rosén**University of Bergen*2 papers here · 47 citations*](https://md.research.elamur.ai/free/en/authors/victoria-rosen/)
18. [**Murhaf Fares**University of Oslo*2 papers here · 33 citations*](https://md.research.elamur.ai/free/en/authors/murhaf-fares/)

## Works in our library (48)

Works of its institutions, the most cited first.

1. **[OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles](https://md.research.elamur.ai/free/en/papers/lison-2016-opensubtitles2016-extracting-large-parallel-corpora/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Pierre Lison, Jörg Tiedemann*2016 · 1,099 citations*
2. **[AdapterHub: A Framework for Adapting Transformers](https://md.research.elamur.ai/free/en/papers/pfeiffer-2020-adapterhub-framework-adapting-transformers/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, et al.*2020 · 748 citations*
3. **[Using Convolutional Neural Networks to Classify Hate-Speech](https://md.research.elamur.ai/free/en/papers/gamback-2017-convolutional-neural-networks-classify-hate/) [Workshop on Abusive Language Online](https://md.research.elamur.ai/free/en/venues/workshop-on-abusive-language-online/)**Björn Gambäck, Utpal Kumar Sikdar*2017 · 651 citations*
4. [**CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies**Daniel Zeman, Martin Popel, Milan Straka, et al.*2017 · 604 citations*](https://md.research.elamur.ai/free/en/papers/zeman-2017-conll-2017-shared-task-multilingual/)
5. [**The Parallel Grammar Project COLING-02: Grammar Engineering and Evaluation**Miriam Butt, Helge Dyvik, Tracy Holloway King, et al.*2002 · 392 citations*](https://md.research.elamur.ai/free/en/papers/butt-2002-parallel-grammar-project/)
6. **[Diachronic word embeddings and semantic shifts: a survey](https://md.research.elamur.ai/free/en/papers/kutuzov-2018-diachronic-word-embeddings-semantic-shifts/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Andrey Kutuzov, Lilja Øvrelid, Terrence Szymanski, et al.*2018 · 283 citations*
7. **[SemEval-2020 Task 8: Memotion Analysis- the Visuo-Lingual Metaphor!](https://md.research.elamur.ai/free/en/papers/sharma-2020-semeval-2020-task-8-memotion/) [International Workshop on Semantic Evaluation (SemEval)](https://md.research.elamur.ai/free/en/venues/semeval/)**Chhavi Sharma, Deepesh Bhageria, William Scott, et al.*2020 · 260 citations*
8. **[SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets](https://md.research.elamur.ai/free/en/papers/patwa-2020-semeval-2020-task-9-overview/) [International Workshop on Semantic Evaluation (SemEval)](https://md.research.elamur.ai/free/en/venues/semeval/)**Parth Patwa, Gustavo Aguilar, Sudipta Kar, et al.*2020 · 240 citations*
9. **[OpenSubtitles2018: Statistical Rescoring of Sentence Alignments in Large, Noisy Parallel Corpora](https://md.research.elamur.ai/free/en/papers/lison-2018-opensubtitles2018-statistical-rescoring-sentence-alignments/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Pierre Lison, Jörg Tiedemann, Milen Kouylekov*2018 · 235 citations*
10. [**A Regression Model of Adjective-Noun Compositionality in Distributional Semantics Proceedings of the 2010 Workshop on GEometrical Models of Natural Language Semantics**Emiliano Guevara*2010 · 203 citations*](https://md.research.elamur.ai/free/en/papers/guevara-2010-regression-model-adjective-noun-compositionality/)
11. [**Discriminant-Based MRS Banking**Stephan Oepen, Jan Tore Lønning*2006 · 184 citations*](https://md.research.elamur.ai/free/en/papers/oepen-2006-discriminant-based-mrs-banking/)
12. **[Zero-Shot Cross-Lingual Transfer with Meta Learning](https://md.research.elamur.ai/free/en/papers/nooralahzadeh-2020-zero-shot-cross-lingual-transfer/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Farhad Nooralahzadeh, Giannis Bekoulis, Johannes Bjerva, et al.*2020 · 171 citations*
13. **[MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/adelani-2022-masakhaner-2-0-africa-centric/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder, et al.*2022 · 150 citations*
14. **[The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://md.research.elamur.ai/free/en/papers/pilan-2022-text-anonymization-benchmark-tab-dedicated/) [Computational Linguistics](https://md.research.elamur.ai/free/en/venues/cl/)**Ildikó Pilán, Pierre Lison, Lilja Øvrelid, et al.*2022 · 129 citations*
15. **[MRP 2020: The Second Shared Task on Cross-Framework and Cross-Lingual Meaning Representation Parsing](https://md.research.elamur.ai/free/en/papers/oepen-2020-mrp-2020-second-shared-task/) [Conference on Computational Natural Language Learning (CoNLL)](https://md.research.elamur.ai/free/en/venues/conll/)**Stephan Oepen, Omri Abend, Lasha Abzianidze, et al.*2020 · 101 citations*
16. **[Road-testing the English Resource Grammar Over the British National Corpus](https://md.research.elamur.ai/free/en/papers/baldwin-2004-road-testing-english-resource-grammar/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Timothy Baldwin, Emily M. Bender, Dan Flickinger, et al.*2004 · 95 citations*
17. **[WikiWoods: Syntacto-Semantic Annotation for English Wikipedia](https://md.research.elamur.ai/free/en/papers/flickinger-2010-wikiwoods-syntacto-semantic-annotation-english/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Dan Flickinger, Stephan Oepen, Gisle Ytrestøl*2010 · 81 citations*
18. [**Sentence Boundary Detection: A Long Solved Problem?**Jonathon Read, Rebecca Dridan, Stephan Oepen, et al.*2012 · 81 citations*](https://md.research.elamur.ai/free/en/papers/read-2012-sentence-boundary-detection-long-solved/)
19. [**Parser Evaluation over Local and Non-Local Deep Dependencies in a Large Corpus**Emily M. Bender, Dan Flickinger, Stephan Oepen, et al.*2011 · 53 citations*](https://md.research.elamur.ai/free/en/papers/bender-2011-parser-evaluation-over-local-non/)
20. [**Tokenization: Returning to a Long Solved Problem – A Survey, Contrastive Experiment, Recommendations, and Toolkit**Rebecca Dridan, Stephan Oepen*2012 · 43 citations*](https://md.research.elamur.ai/free/en/papers/dridan-2012-tokenization-returning-long-solved-problem/)
21. [**Anticausatives are semantically reflexive in Norwegian, but not in English**Björn Lundquist, Martin Corley, Mai Tungseth, et al.*2016 · 41 citations*](https://md.research.elamur.ai/free/en/papers/lundquist-2016-anticausatives-are-semantically-reflexive-norwegian/)
22. [**Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis**Mario Giulianelli, Iris Luden, Raquel Fernandez, et al.*2023 · 40 citations*](https://md.research.elamur.ai/free/en/papers/giulianelli-2023-definition-generation-senses/)
23. [**The 2018 Shared Task on Extrinsic Parser Evaluation: On the Downstream Utility of English Universal Dependency Parsers**Murhaf Fares, Stephan Oepen, Lilja Øvrelid, et al.*2018 · 27 citations*](https://md.research.elamur.ai/free/en/papers/fares-2018-2018-shared-task-extrinsic-parser/)
24. **[OPT: Oslo–Potsdam–Teesside. Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing](https://md.research.elamur.ai/free/en/papers/oepen-2016-opt-oslo-potsdam-teesside-pipelining/) [Conference on Computational Natural Language Learning (CoNLL)](https://md.research.elamur.ai/free/en/venues/conll/)**Stephan Oepen, Jonathon Read, Tatjana Scheffler, et al.*2016 · 26 citations*
25. **[An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)](https://md.research.elamur.ai/free/en/papers/burchell-2025-expanded-massive-multilingual-dataset-high/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Laurie Burchell, Ona de Gibert, Nikolay Arefyev, et al.*2025 · 23 citations*

[See all 48 works in Norway →](https://md.research.elamur.ai/free/en/countries/norway/works/)

## Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 15 The field of science this work belongs to (OpenAlex fields).[Computer Science · 37 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 36 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 45 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 44 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Psychology · 7 works](https://md.research.elamur.ai/free/en/shelves/psychology/) · [Experimental and Cognitive Psychology · 5 works](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Philosophy · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/philosophy/) · [Cognitive Neuroscience · 1 work](https://md.research.elamur.ai/free/en/shelves/neuroscience/cognitive-neuroscience/) · [Neuroscience · 1 work](https://md.research.elamur.ai/free/en/shelves/neuroscience/) · [Religious studies · 5 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/religious-studies/) · [Literature and Literary Theory · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/literature-and-literary-theory/) · [Developmental and Educational Psychology · 2 works](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · [Information Systems · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Medicine · 1 work](https://md.research.elamur.ai/free/en/shelves/medicine/)

🧭 Topics 25 Research subjects and languages the work is about.[English · 16 works](https://md.research.elamur.ai/free/en/topics/english/) · [Multilingual & cross-lingual NLP · 6 works](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Syntax & grammar formalisms · 2 works](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) · [Sentiment & emotion · 2 works](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Historical linguistics & language change · 5 works](https://md.research.elamur.ai/free/en/topics/language-change/) · [Evaluation & benchmarks · 6 works](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Idioms & multiword expressions · 3 works](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) · [Universal Dependencies · 3 works](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) · [Bias, fairness & safety · 1 work](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Named entity recognition · 1 work](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · [Tokenization & segmentation · 2 works](https://md.research.elamur.ai/free/en/topics/tokenization/) · [Discourse analysis · 1 work](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · [Semantic parsing & meaning representation · 1 work](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) · [Coreference resolution · 2 works](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · [Machine translation · 2 works](https://md.research.elamur.ai/free/en/topics/machine-translation/)+10 more

💡 Concepts 6 Key ideas and methods explained on our concept pages.[Semantics · 2 works](https://md.research.elamur.ai/free/en/concepts/semantics/) · [Cognitive linguistics · 1 work](https://md.research.elamur.ai/free/en/concepts/cognitive-linguistics/) · [Morphology · 1 work](https://md.research.elamur.ai/free/en/concepts/morphology/) · [Parsing · 1 work](https://md.research.elamur.ai/free/en/concepts/parsing/) · [Universal Dependencies · 1 work](https://md.research.elamur.ai/free/en/concepts/universal-dependencies/) · [Distributional semantics · 1 work](https://md.research.elamur.ai/free/en/concepts/distributional-semantics/)

## Works by year

### 2020s

[**2026** 5 works Works of Norway from 2026](https://md.research.elamur.ai/free/en/countries/norway/year/2026/) · [**2025** 2 works Works of Norway from 2025](https://md.research.elamur.ai/free/en/countries/norway/year/2025/) · [**2024** 1 work Works of Norway from 2024](https://md.research.elamur.ai/free/en/papers/bech-2024-noun-phrases-early-germanic/) · [**2023** 1 work Works of Norway from 2023](https://md.research.elamur.ai/free/en/papers/giulianelli-2023-definition-generation-senses/) · [**2022** 3 works Works of Norway from 2022](https://md.research.elamur.ai/free/en/countries/norway/year/2022/) · [**2020** 6 works Works of Norway from 2020](https://md.research.elamur.ai/free/en/countries/norway/year/2020/)

### 2010s

[**2019** 3 works Works of Norway from 2019](https://md.research.elamur.ai/free/en/countries/norway/year/2019/) · [**2018** 4 works Works of Norway from 2018](https://md.research.elamur.ai/free/en/countries/norway/year/2018/) · [**2017** 7 works Works of Norway from 2017](https://md.research.elamur.ai/free/en/countries/norway/year/2017/) · [**2016** 5 works Works of Norway from 2016](https://md.research.elamur.ai/free/en/countries/norway/year/2016/) · [**2013** 1 work Works of Norway from 2013](https://md.research.elamur.ai/free/en/papers/holen-2013-critical-reflections-evaluation-practices-coreference/) · [**2012** 3 works Works of Norway from 2012](https://md.research.elamur.ai/free/en/countries/norway/year/2012/) · [**2011** 1 work Works of Norway from 2011](https://md.research.elamur.ai/free/en/papers/bender-2011-parser-evaluation-over-local-non/) · [**2010** 2 works Works of Norway from 2010](https://md.research.elamur.ai/free/en/countries/norway/year/2010/)

### 2000s

[**2006** 1 work Works of Norway from 2006](https://md.research.elamur.ai/free/en/papers/oepen-2006-discriminant-based-mrs-banking/) · [**2004** 1 work Works of Norway from 2004](https://md.research.elamur.ai/free/en/papers/baldwin-2004-road-testing-english-resource-grammar/) · [**2002** 1 work Works of Norway from 2002](https://md.research.elamur.ai/free/en/papers/butt-2002-parallel-grammar-project/)

### 1990s

[**1997** 1 work Works of Norway from 1997](https://md.research.elamur.ai/free/en/papers/borthen-1997-what-brings-higher-order-entity/)

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

Updated 24 October 2026