---
title: "Automatic Lemmatisation for Norwegian — Yildirim 2026"
description: "Lemmatising Norwegian is difficult. 19 references. Among them: 0."
authors: ["Ahmet Yildirim", "Kristin Hagen", "Dag Haug"]
year: 2026
venue: "Proceedings of the Workshop on Structured Linguistic Data and Evaluation (SLiDE)"
source: "https://aclanthology.org/2026.slide-1.8/"
doi: "10.63317/2cpfp5inka2c"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yildirim-2026-automatic-lemmatisation-norwegian/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yildirim-2026-automatic-lemmatisation-norwegian/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/) / Automatic Lemmatisation for Norwegian

# Automatic Lemmatisation for Norwegian

**Authors:** Ahmet Yildirim, Kristin Hagen and [Dag Haug](https://md.research.elamur.ai/free/en/authors/dag-haug/) · **Year:** 2026 · **Venue:** [Proceedings of the Workshop on Structured Linguistic Data and Evaluation (SLiDE)](https://md.research.elamur.ai/free/en/venues/slide/) ([SLiDE 2026](https://md.research.elamur.ai/free/en/venues/slide/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.slide-1.8/) · [PDF](https://aclanthology.org/2026.slide-1.8.pdf) · [DOI 10.63317/2cpfp5inka2c](https://doi.org/10.63317/2cpfp5inka2c) · [OpenAlex](https://openalex.org/W7166573042)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Lemmatising Norwegian is difficult. The language has two written standards, Bokmål and Nynorsk, which can be indistinguishable in short sentences, and both allow a lot of spelling optionality even in base forms (e.g. tenka/tenke/tenkja/tenkje). The authors built a lemmatiser that covers both varieties for the Humit tagger at the University of Oslo. Its neural component follows the UDpipe approach (Straka et al., 2019): fine-tuned BERT models assign each token to a class of edit rules that turns the word into its lemma. This component is combined with Norsk ordbank, a large computational lexicon that lists full inflectional paradigms. The authors compare two hybrid ways of intersecting these components against a purely neural setup, using data from the Norwegian Dependency Treebank. Under plain string matching, all configurations score nearly the same. However, a manual error analysis that separates genuine mistakes from acceptable alternative spellings shows that the lexicon removes more than half of the real errors. The broader lesson is that structured lexical resources, even simple dictionaries, can filter implausible neural output and improve user trust.

## Key points
- Data: the Norwegian Dependency Treebank, split by the authors 0.9/0.1 because it has no official split. The training set contains 280,369 Bokmål and 272,355 Nynorsk words, and the test set contains 30,650 and 30,712 words respectively.
- Raw string-match accuracy is 99.1–99.2% on Bokmål and 98.5–98.6% on Nynorsk for every configuration.
- When equally valid spelling variants are not counted as errors, the lexicon-based hybrids reach 99.6% (Bokmål) and 99.3% (Nynorsk).
- Earlier baselines: OBT+stat achieved 98.48% on Bokmål only, and NorBench reported 99.1% on the Norwegian UD treebanks but did not release its fine-tuned models.
- Lexical resource: Norsk ordbank (Bokmål and Nynorsk), maintained by the Norwegian language council and the University of Bergen. Its paradigms carry validity dates that reflect spelling reforms, most recently in 2005 for Bokmål and 2012 for Nynorsk.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Oslo](https://md.research.elamur.ai/free/en/universities/university-of-oslo/) — University, Oslo, Norway · 51 works · 4,155 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🧩 Morphology](https://md.research.elamur.ai/free/en/topics/morphology/) · 405 works

💡 Concepts (1): [💡 Lemmatization](https://md.research.elamur.ai/free/en/concepts/lemmatization/) · 20 works

## Cite

Cite as: Ahmet Yildirim, Kristin Hagen and Dag Haug. 2026. Automatic Lemmatisation for Norwegian. Proceedings of the Workshop on Structured Linguistic Data and Evaluation (SLiDE).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yildirim2026automatic,
  title = {{Automatic Lemmatisation for Norwegian}},
  author = {Ahmet Yildirim, Kristin Hagen and Dag Haug},
  booktitle = {Proceedings of the Workshop on Structured Linguistic Data and Evaluation (SLiDE)},
  year = {2026},
  doi = {10.63317/2cpfp5inka2c},
  url = {https://doi.org/10.63317/2cpfp5inka2c}
}
```

- [← previous Automatic Generation of Graded Texts in Old Church Slavonic](https://md.research.elamur.ai/free/en/papers/stoupak-2026-automatic-generation-graded-texts-old/)
- [next → Automatic Paper Analysis and Categorisation for Systematic Reviews with Combined Reasoning-Augmented SFT and DAPO RL](https://md.research.elamur.ai/free/en/papers/lorandi-2026-automatic-paper-analysis-categorisation-systematic/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/)

## References

19 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tove Fjeldvig and Anne Golden. 1984. Automatisk rotlemmatisering (automatic root lemmatization) [in Norwegian]. In Proceedings of the 4th Nordic Conference of Computational Linguistics (NODALIDA 1983), pages 84–103, Uppsala, Sweden. Centrum för datorlingvistik, Uppsala University, Sweden. [find](https://scholar.google.com/scholar?q=Tove+Fjeldvig+and+Anne+Golden%2E+1984%2E+Automatisk+rotlemmatisering+%28automatic+root+lemmatization%29+%5Bin+Norwegian%5D%2E+In+Proceedings+of+the+4th+Nordic+Conference+of+Computational+Linguistics+%28NODALIDA+1983%29)
2. Emiliano Raul Guevara. 2010. NoWaC: a large web-based corpus for Norwegian. In Proceedings of the NAACL HLT 2010 Sixth Web as Corpus Workshop, pages 1–7, NAACL-HLT, Los Angeles. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Emiliano+Raul+Guevara%2E+2010%2E+NoWaC%3A+a+large+web%2Dbased+corpus+for+Norwegian%2E+In+Proceedings+of+the+NAACL+HLT+2010+Sixth+Web+as+Corpus+Workshop%2C+pages+1%E2%80%937%2C+NAACL%2DHLT%2C+Los+Angeles%2E+Association+for+Comput)
3. Dag Haug, Ahmet Yildirim, Kristin Hagen, and Anders Nøklestad. 2023. Rules and neural nets for morphological tagging of Norwegian - results and challenges. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 425–435, Tórshavn, Faroe Islands. University of Tartu Library. [find](https://scholar.google.com/scholar?q=Dag+Haug%2C+Ahmet+Yildirim%2C+Kristin+Hagen%2C+and+Anders+N%C3%B8klestad%2E+2023%2E+Rules+and+neural+nets+for+morphological+tagging+of+Norwegian+%2D+results+and+challenges%2E+In+Proceedings+of+the+24th+Nordic+Conference)
4. Janne Bondi Johannessen and Kristin Hagen. 2003. Parsing nordic languages (panola) norsk versjon. In Henrik Holmboe, editor, Nordisk Sprogteknologi 2002, pages 89–95. Museum Tusculanums Press. [find](https://scholar.google.com/scholar?q=Janne+Bondi+Johannessen+and+Kristin+Hagen%2E+2003%2E+Parsing+nordic+languages+%28panola%29+norsk+versjon%2E+In+Henrik+Holmboe%2C+editor%2C+Nordisk+Sprogteknologi+2002%2C+pages+89%E2%80%9395%2E+Museum+Tusculanums+Press%2E)
5. Janne Bondi Johannessen, Kristin Hagen, André Lynum, and Anders Nøklestad. 2012. Obt+stat: A combined rule-based and statistical tagger. In Gisle Andersen, editor, Exploring Newspaper Language, pages 51–66. John Benjamins Publishing Company. [find](https://scholar.google.com/scholar?q=Janne+Bondi+Johannessen%2C+Kristin+Hagen%2C+Andr%C3%A9+Lynum%2C+and+Anders+N%C3%B8klestad%2E+2012%2E+Obt%2Bstat%3A+A+combined+rule%2Dbased+and+statistical+tagger%2E+In+Gisle+Andersen%2C+editor%2C+Exploring+Newspaper+Language%2C+pages+)
6. Thomas Karterud, Kristin Rogge Pran, and Mathilde Horvei. 2024. Språkrådets brukerog befolkningsundersøkelse. [https://sprakradet.no/wp-content/uploads/Sprakradets-Bruker-og-befolkningsundersokelse-2024.pdf](https://sprakradet.no/wp-content/uploads/Sprakradets-Bruker-og-befolkningsundersokelse-2024.pdf). Accessed: 2026-02-16. [↗](https://sprakradet.no/wp-content/uploads/Sprakradets-Bruker-og-befolkningsundersokelse-2024.pdf)
7. Per E Kummervold, Javier De la Rosa, Freddy Wetjen, and Svein Arne Brygfjeld. 2021. Operationalizing a national digital library: The case for a Norwegian transformer model. In Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), pages 20–29, Reykjavik, Iceland (Online). Linköping University Electronic Press, Sweden. [↗](https://doi.org/10.48550/arxiv.2104.09617)
8. Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Christo Kirov, Miikka Silfverberg, Sabrina J. Mielke, Jeffrey Heinz, Ryan Cotterell, and Mans Hulden. 2019. [find](https://scholar.google.com/scholar?q=Arya+D%2E+McCarthy%2C+Ekaterina+Vylomova%2C+Shijie+Wu%2C+Chaitanya+Malaviya%2C+Lawrence+Wolf%2DSonkin%2C+Garrett+Nicolai%2C+Christo+Kirov%2C+Miikka+Silfverberg%2C+Sabrina+J%2E+Mielke%2C+Jeffrey+Heinz%2C+Ryan+Cotterell%2C+and+Man)
9. The SIG-MORPHON 2019 shared task: Morphological analysis in context and cross-lingual transfer for inflection. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 229–244, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=The+SIG%2DMORPHON+2019+shared+task%3A+Morphological+analysis+in+context+and+cross%2Dlingual+transfer+for+inflection%2E+In+Proceedings+of+the+16th+Workshop+on+Computational+Research+in+Phonetics%2C+Phonology%2C+an)
10. Kirill Milintsevich and Kairit Sirts. 2021. Enhancing sequence-to-sequence neural lemmatization with external resources. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3112–3122, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kirill+Milintsevich+and+Kairit+Sirts%2E+2021%2E+Enhancing+sequence%2Dto%2Dsequence+neural+lemmatization+with+external+resources%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+of+the+Associatio)
11. Lilja Øvrelid and Petter Hohle. 2016. Universal Dependencies for Norwegian. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 1579–1585, Portorož, Slovenia. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Lilja+%C3%98vrelid+and+Petter+Hohle%2E+2016%2E+Universal+Dependencies+for+Norwegian%2E+In+Proceedings+of+the+Tenth+International+Conference+on+Language+Resources+and+Evaluation+%28LREC%E2%80%9916%29%2C+pages+1579%E2%80%931585%2C+Portor)
12. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. [Stanza: A python natural language processing toolkit for many human languages](https://md.research.elamur.ai/free/en/papers/qi-2020-stanza-python-natural-language-processing/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 101–108, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.acl-demos.14)
13. David Samuel, Andrey Kutuzov, Samia Touileb, Erik Velldal, Lilja Øvrelid, Egil Rønningstad, Elina Sigdel, and Anna Palatkina. 2023. Nor-Bench – a benchmark for Norwegian language models. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 618–633, Tórshavn, Faroe Islands. University of Tartu Library. [find](https://scholar.google.com/scholar?q=David+Samuel%2C+Andrey+Kutuzov%2C+Samia+Touileb%2C+Erik+Velldal%2C+Lilja+%C3%98vrelid%2C+Egil+R%C3%B8nningstad%2C+Elina+Sigdel%2C+and+Anna+Palatkina%2E+2023%2E+Nor%2DBench+%E2%80%93+a+benchmark+for+Norwegian+language+models%2E+In+Proceeding)
14. Per Erik Solberg, Arne Skjærholt, Lilja Øvrelid, Kristin Hagen, and Janne Bondi Johannessen. 2014. The Norwegian dependency treebank. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 789–795, Reykjavik, Iceland. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Per+Erik+Solberg%2C+Arne+Skj%C3%A6rholt%2C+Lilja+%C3%98vrelid%2C+Kristin+Hagen%2C+and+Janne+Bondi+Johannessen%2E+2014%2E+The+Norwegian+dependency+treebank%2E+In+Proceedings+of+the+Ninth+International+Conference+on+Language+R)
15. Milan Straka, Jana Straková, and Jan Hajic. 2019. UDPipe at SIGMORPHON 2019: Contextualized embeddings, regularization with morphological categories, corpora merging. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 95–103, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Milan+Straka%2C+Jana+Strakov%C3%A1%2C+and+Jan+Hajic%2E+2019%2E+UDPipe+at+SIGMORPHON+2019%3A+Contextualized+embeddings%2C+regularization+with+morphological+categories%2C+corpora+merging%2E+In+Proceedings+of+the+16th+Worksh)
16. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in neural information processing systems, pages 5998–6008. 10. Language Resource References National Library of Norway. 2014. The Norwegian dependency treebank. National Library of Norway. PID [https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-10/](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-10/). [↗](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-10/)
17. National Library of Norway. 2022a. Norsk ordbank bokmål. National Library of Norway. PID [https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-5/](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-5/). [↗](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-5/)
18. National Library of Norway. 2022b. Norsk ordbank nynorsk. National Library of Norway. PID [https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-41/](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-41/). [↗](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-41/)
19. National Library of Norway. 2023. Norwegian UD treebank. National Library of Norway. PID [https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-83/](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-83/). [↗](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-83/)

*Updated 1 November 2026*