---
title: "Improving Latvian Morphosyntactic Parsing — Znotins 2026"
description: "Latvian is a heavily inflected Baltic language. Its native XPOS tagset is very fine-grained, which makes automatic tagging, lemmatization and dependency…"
authors: ["Arturs Znotins"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.918/"
doi: "10.63317/5khpzsaiqrzw"
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/znotins-2026-improving-latvian-morphosyntactic-parsing-pretrained/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/znotins-2026-improving-latvian-morphosyntactic-parsing-pretrained/)

[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/5/) / Improving Latvian Morphosyntactic Parsing with Pretrained Encoders and Analyzer-Constrained Decoding

# Improving Latvian Morphosyntactic Parsing with Pretrained Encoders and Analyzer-Constrained Decoding

**Authors:** Arturs Znotins · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **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.lrec-1.918/) · [PDF](https://aclanthology.org/2026.lrec-1.918.pdf) · [DOI 10.63317/5khpzsaiqrzw](https://doi.org/10.63317/5khpzsaiqrzw) · [OpenAlex](https://openalex.org/W7160042364)

**Citations:** 1 citations (openalex-snapshot · 2026-10-14)

## Summary
Latvian is a heavily inflected Baltic language. Its native XPOS tagset is very fine-grained, which makes automatic tagging, lemmatization and dependency parsing hard because many labels are rare. The author benchmarks several pretrained transformer encoders, both multilingual and Latvian-specific, inside one shared multi-task architecture. The architecture uses layer mixtures per task, UPOS-conditioned heads, rule-based lemma edits and a biaffine parser. Training and evaluation use the Latvian UD treebank. The study tests three ideas:
- adapting encoders to Latvian with a modest corpus of about 1B tokens, either through continued pretraining or by training RoBERTa-style models from scratch;
- splitting morphological tags into separate attributes instead of predicting whole tags;
- restricting outputs to candidates proposed by a lexicon-based Latvian morphological analyzer.

Language-specific adaptation clearly helps, even with limited data. The factored tags make the model more robust, and the analyzer constraints improve XPOS and lemma accuracy even for strong encoders. The resulting system sets a new state of the art for Latvian. This matters for large-scale corpus annotation, and the models and code are released openly.

## Key points
- **Data:** UD v2.17 Latvian treebank (LVTB), about 19,000 sentences and 330,000 tokens. Encoder adaptation uses a corpus of roughly 1B tokens drawn from LNCC, which includes news, web, LVK2022, legal texts, Wikipedia, Saeima debates, theses and blogs.
- **Tagset sparsity:** the Latvian XPOS tagset has 34 attributes and around 1,800 distinct tags. The analyzer (Paikens et al., 2024) covers more than 118,000 lexemes, mostly taken from Tēzaurs.lv.
- **Best results:** the top system reaches 95.22% on XPOS tagging, 98.72% on lemmatization, and a LAS of 93.19%. The earlier LVTagger baseline reached 93.44% XPOS and 98.41% lemma accuracy.
- **Setup:** results are averaged over five random seeds. The lemmatization loss is weighted at 4, compared with 1 for the other tasks. Trees are decoded with a maximum spanning tree algorithm (Chu–Liu/Edmonds) under a single-root constraint.
- **Availability:** models and code are public at github.com/LUMII-AILab/lvnlp.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/)

## Cite

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

```bibtex
@inproceedings{znotins2026improving,
  title = {{Improving Latvian Morphosyntactic Parsing with Pretrained Encoders and Analyzer-Constrained Decoding}},
  author = {Znotins, Arturs},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5khpzsaiqrzw},
  url = {https://doi.org/10.63317/5khpzsaiqrzw}
}
```

- [← previous Improving Dialect Robustness in Large Language Models via LoRA and Mixture-of-Experts](https://md.research.elamur.ai/free/en/papers/maheshwari-2026-improving-dialect-robustness-large-language/)
- [next → In-Distribution Steering: Balancing Control and Coherence in Language Model Generation](https://md.research.elamur.ai/free/en/papers/vogels-2026-distribution-steering-balancing-control-coherence/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/)

## References

37 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Guntis Barzdins, Normunds Gruzitis, Gunta Nespore, and Baiba Saulite. 2007. Dependency-based hybrid model of syntactic analysis for the languages with a rather free word order. In Proceedings of the 16th Nordic Conference of Computational Linguistics, pages 13–20, Tartu, Estonia. [find](https://scholar.google.com/scholar?q=Guntis+Barzdins%2C+Normunds+Gruzitis%2C+Gunta+Nespore%2C+and+Baiba+Saulite%2E+2007%2E+Dependency%2Dbased+hybrid+model+of+syntactic+analysis+for+the+languages+with+a+rather+free+word+order%2E+In+Proceedings+of+the+1)
2. Bernd Bohnet and Joakim Nivre. 2012. A transition-based system for joint part-of-speech tagging and labeled non-projective dependency parsing. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1455–1465,… [find](https://scholar.google.com/scholar?q=Bernd+Bohnet+and+Joakim+Nivre%2E+2012%2E+A+transition%2Dbased+system+for+joint+part%2Dof%2Dspeech+tagging+and+labeled+non%2Dprojective+dependency+parsing%2E+In+Proceedings+of+the+2012+Joint+Conference+on+Empirical+) [our card](https://md.research.elamur.ai/free/en/papers/bohnet-2012-transition-based-system-joint-part/)
3. Laurie Burchell, Ona de Gibert, Nikolay Arefyev, Mikko Aulamo, Marta Bañón, Pinzhen Chen, Mariia Fedorova, Liane Guillou, Barry Haddow, Jan Hajič, Jindřich Helcl, Erik Henriksson, Mateusz Klimaszewski, Ville Komulainen, Andrey Kutuzov, Joona Kytöniemi, Veronika Laippala, Petter Mæhlum, Bhavitvya Mal… [find](https://scholar.google.com/scholar?q=Laurie+Burchell%2C+Ona+de+Gibert%2C+Nikolay+Arefyev%2C+Mikko+Aulamo%2C+Marta+Ba%C3%B1%C3%B3n%2C+Pinzhen+Chen%2C+Mariia+Fedorova%2C+Liane+Guillou%2C+Barry+Haddow%2C+Jan+Haji%C4%8D%2C+Jind%C5%99ich+Helcl%2C+Erik+Henriksson%2C+Mateusz+Klimaszewski) [our card](https://md.research.elamur.ai/free/en/papers/burchell-2025-expanded-massive-multilingual-dataset-high/)
4. Yoeng-Jin Chu. 1965. On the shortest arborescence of a directed graph. Scientia Sinica, 14:1396–1400. [find](https://scholar.google.com/scholar?q=Yoeng%2DJin+Chu%2E+1965%2E+On+the+shortest+arborescence+of+a+directed+graph%2E+Scientia+Sinica%2C+14%3A1396%E2%80%931400%2E)
5. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association fo… [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Kartikay+Khandelwal%2C+Naman+Goyal%2C+Vishrav+Chaudhary%2C+Guillaume+Wenzek%2C+Francisco+Guzm%C3%A1n%2C+Edouard+Grave%2C+Myle+Ott%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2020%2E+Unsupervised+cross%2Dlingu)
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+In+Proceedings+of+the+2019+Conference+of+the+N)
7. Timothy Dozat and Christopher D. Manning. 2017. Deep biaffine attention for neural dependency parsing. In Proceedings of the International Conference on Learning Representations (ICLR) 2017. Poster. [find](https://scholar.google.com/scholar?q=Timothy+Dozat+and+Christopher+D%2E+Manning%2E+2017%2E+Deep+biaffine+attention+for+neural+dependency+parsing%2E+In+Proceedings+of+the+International+Conference+on+Learning+Representations+%28ICLR%29+2017%2E+Poster%2E) [our card](https://md.research.elamur.ai/free/en/papers/missing-2016-dozat-deep-biaffine-attention-neural-dependency/)
8. Jack Edmonds. 1967. Optimum branchings. Journal of Research of the National Bureau of Standards – B. Mathematics and Mathematical Physics, 71B(4):233–240. [find](https://scholar.google.com/scholar?q=Jack+Edmonds%2E+1967%2E+Optimum+branchings%2E+Journal+of+Research+of+the+National+Bureau+of+Standards+%E2%80%93+B%2E+Mathematics+and+Mathematical+Physics%2C+71B%284%29%3A233%E2%80%93240%2E)
9. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. [find](https://scholar.google.com/scholar?q=Pengcheng+He%2C+Jianfeng+Gao%2C+and+Weizhu+Chen%2E+2023%2E+Debertav3%3A+Improving+deberta+using+electra%2Dstyle+pre%2Dtraining+with+gradient%2Ddisentangled+embedding+sharing%2E) [our card](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/)
10. Go Inoue, Salam Khalifa, and Nizar Habash. 2022. Morphosyntactic tagging with pre-trained language models for Arabic and its dialects. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1708–1719, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Go+Inoue%2C+Salam+Khalifa%2C+and+Nizar+Habash%2E+2022%2E+Morphosyntactic+tagging+with+pre%2Dtrained+language+models+for+Arabic+and+its+dialects%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL)
11. Alek Keersmaekers and Wouter Mercelis. 2024. Adapting transformer models to morphological tagging of two highly inflectional languages: a case study on Ancient Greek and Latin. In Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024), pages 165–176, Hybrid in Bangkok… [find](https://scholar.google.com/scholar?q=Alek+Keersmaekers+and+Wouter+Mercelis%2E+2024%2E+Adapting+transformer+models+to+morphological+tagging+of+two+highly+inflectional+languages%3A+a+case+study+on+Ancient+Greek+and+Latin%2E+In+Proceedings+of+the+1)
12. Dan Kondratyuk and Milan Straka. 2019. 75 languages, 1 model: Parsing Universal Dependencies universally. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2779–279… [find](https://scholar.google.com/scholar?q=Dan+Kondratyuk+and+Milan+Straka%2E+2019%2E+75+languages%2C+1+model%3A+Parsing+Universal+Dependencies+universally%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing+and+) [our card](https://md.research.elamur.ai/free/en/papers/ud-2019-kondratyuk-75-languages-1-model-parsing/)
13. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+Roberta%3A+A+robustly+optimized+bert+pretraining+approach%2E+a)
14. Gunta Nespore, Baiba Saulite, Guntis Barzdins, and Normunds Gruzitis. 2010. Comparison of the SemTi-Kamols and Tesniere’s dependency grammars. In Human Language Technologies – The Baltic Perspective, volume 219 of Frontiers in Artificial Intelligence and Applications, pages 233–240. IOS Press. [find](https://scholar.google.com/scholar?q=Gunta+Nespore%2C+Baiba+Saulite%2C+Guntis+Barzdins%2C+and+Normunds+Gruzitis%2E+2010%2E+Comparison+of+the+SemTi%2DKamols+and+Tesniere%E2%80%99s+dependency+grammars%2E+In+Human+Language+Technologies+%E2%80%93+The+Baltic+Perspective%2C+)
15. Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh, and Thien Huu Nguyen. 2021. Trankit: A light-weight transformer-based toolkit for multilingual natural language processing. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System De… [find](https://scholar.google.com/scholar?q=Minh+Van+Nguyen%2C+Viet+Dac+Lai%2C+Amir+Pouran+Ben+Veyseh%2C+and+Thien+Huu+Nguyen%2E+2021%2E+Trankit%3A+A+light%2Dweight+transformer%2Dbased+toolkit+for+multilingual+natural+language+processing%2E+In+Proceedings+of+the) [our card](https://md.research.elamur.ai/free/en/papers/ud-2021-nguyen-trankit-light-weight-transformer-based/)
16. Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Jan Hajič, Christopher D. Manning, Sampo Pyysalo, Sebastian Schuster, Francis Tyers, and Daniel Zeman. 2020. Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection. In Proceedings of the 12th Language Resources and Evaluati… [find](https://scholar.google.com/scholar?q=Joakim+Nivre%2C+Marie%2DCatherine+de+Marneffe%2C+Filip+Ginter%2C+Jan+Haji%C4%8D%2C+Christopher+D%2E+Manning%2C+Sampo+Pyysalo%2C+Sebastian+Schuster%2C+Francis+Tyers%2C+and+Daniel+Zeman%2E+2020%2E+Universal+Dependencies+v2%3A+An+Ever)
17. Peteris Paikens. 2016. Deep Neural Learning Approaches for Latvian Morphological Tagging. In Human Language Technologies - The Baltic Perspective, volume 289. IOS Press. [find](https://scholar.google.com/scholar?q=Peteris+Paikens%2E+2016%2E+Deep+Neural+Learning+Approaches+for+Latvian+Morphological+Tagging%2E+In+Human+Language+Technologies+%2D+The+Baltic+Perspective%2C+volume+289%2E+IOS+Press%2E)
18. Peteris Paikens, Lauma Pretkalnin , a, and Laura Rituma. 2024. A computational model of latvian morphology. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 221–232. [find](https://scholar.google.com/scholar?q=Peteris+Paikens%2C+Lauma+Pretkalnin+%2C+a%2C+and+Laura+Rituma%2E+2024%2E+A+computational+model+of+latvian+morphology%2E+In+Proceedings+of+the+2024+Joint+International+Conference+on+Computational+Linguistics%2C+Lang)
19. Peteris Paikens, Laura Rituma, and Lauma Pretkalnina. 2013. Morphological analysis with limited resources: Latvian example. In Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA), pages 267–277, Oslo, Norway. [find](https://scholar.google.com/scholar?q=Peteris+Paikens%2C+Laura+Rituma%2C+and+Lauma+Pretkalnina%2E+2013%2E+Morphological+analysis+with+limited+resources%3A+Latvian+example%2E+In+Proceedings+of+the+19th+Nordic+Conference+of+Computational+Linguistics+%28N)
20. Lauma Pretkalnina, Gunta Nespore, Kristine Levane-Petrova, and Baiba Saulite. 2011. A Prague Markup Language profile for the SemTi-Kamols grammar model. In Proceedings of the 18th Nordic Conference of Computational Linguistics, pages 303–306, Riga, Latvia. [find](https://scholar.google.com/scholar?q=Lauma+Pretkalnina%2C+Gunta+Nespore%2C+Kristine+Levane%2DPetrova%2C+and+Baiba+Saulite%2E+2011%2E+A+Prague+Markup+Language+profile+for+the+SemTi%2DKamols+grammar+model%2E+In+Proceedings+of+the+18th+Nordic+Conference+of) [our card](https://md.research.elamur.ai/free/en/papers/a-2011-prague-markup-language-profile-semti/)
21. Lauma Pretkalnina, Laura Rituma, and Baiba Saulite. 2018. Deriving Enhanced Universal Dependencies from a Hybrid Dependency-Constituency Treebank. In Text, Speech, and Dialogue, volume 11107, pages 95–105. Springer. [find](https://scholar.google.com/scholar?q=Lauma+Pretkalnina%2C+Laura+Rituma%2C+and+Baiba+Saulite%2E+2018%2E+Deriving+Enhanced+Universal+Dependencies+from+a+Hybrid+Dependency%2DConstituency+Treebank%2E+In+Text%2C+Speech%2C+and+Dialogue%2C+volume+11107%2C+pages+95)
22. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python natural language processing toolkit for many human languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. [find](https://scholar.google.com/scholar?q=Peng+Qi%2C+Yuhao+Zhang%2C+Yuhui+Zhang%2C+Jason+Bolton%2C+and+Christopher+D%2E+Manning%2E+2020%2E+Stanza%3A+A+Python+natural+language+processing+toolkit+for+many+human+languages%2E+In+Proceedings+of+the+58th+Annual+Meet) [our card](https://md.research.elamur.ai/free/en/papers/ud-2020-qi-stanza-python-natural-language-processing/)
23. Baiba Saulite, Roberts Dargis, and Normunds Gruzitis et al. 2022. Latvian National Corpora Collection – Korpuss.lv. In Proceedings of the 13th Language Resources and Evaluation Conference (LREC). [find](https://scholar.google.com/scholar?q=Baiba+Saulite%2C+Roberts+Dargis%2C+and+Normunds+Gruzitis+et+al%2E+2022%2E+Latvian+National+Corpora+Collection+%E2%80%93+Korpuss%2Elv%2E+In+Proceedings+of+the+13th+Language+Resources+and+Evaluation+Conference+%28LREC%29%2E)
24. Andrejs Spektors, Ilze Auzina, and Roberts Dargis et al. 2016. Tezaurs.lv: the largest open lexical database for Latvian. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC). [find](https://scholar.google.com/scholar?q=Andrejs+Spektors%2C+Ilze+Auzina%2C+and+Roberts+Dargis+et+al%2E+2016%2E+Tezaurs%2Elv%3A+the+largest+open+lexical+database+for+Latvian%2E+In+Proceedings+of+the+10th+International+Conference+on+Language+Resources+and+)
25. Milan Straka. 2018. UDPipe 2.0 prototype at CoNLL 2018 UD shared task. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 197–207, Brussels, Belgium. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Milan+Straka%2E+2018%2E+UDPipe+2%2E0+prototype+at+CoNLL+2018+UD+shared+task%2E+In+Proceedings+of+the+CoNLL+2018+Shared+Task%3A+Multilingual+Parsing+from+Raw+Text+to+Universal+Dependencies%2C+pages+197%E2%80%93207%2C+Brusse) [our card](https://md.research.elamur.ai/free/en/papers/ud-2018-straka-udpipe-2-0-prototype-conll/)
26. Alexander Tkachenko and Kairit Sirts. 2018. Modeling composite labels for neural morphological tagging. arXiv preprint arXiv:1810.08815. [find](https://scholar.google.com/scholar?q=Alexander+Tkachenko+and+Kairit+Sirts%2E+2018%2E+Modeling+composite+labels+for+neural+morphological+tagging%2E+arXiv+preprint+arXiv%3A1810%2E08815%2E)
27. Reut Tsarfaty, Djamé Seddah, Sandra Kübler, and Joakim Nivre. 2013. Parsing morphologically rich languages: Introduction to the special issue. Computational Linguistics, 39(1):15–22. [find](https://scholar.google.com/scholar?q=Reut+Tsarfaty%2C+Djam%C3%A9+Seddah%2C+Sandra+K%C3%BCbler%2C+and+Joakim+Nivre%2E+2013%2E+Parsing+morphologically+rich+languages%3A+Introduction+to+the+special+issue%2E+Computational+Linguistics%2C+39%281%29%3A15%E2%80%9322%2E)
28. Matej Ulčar and Marko Robnik-Šikonja. 2021. Training dataset and dictionary sizes matter in bert models: the case of baltic languages. In International conference on analysis of images, social networks and texts, pages 162–172. Springer. [find](https://scholar.google.com/scholar?q=Matej+Ul%C4%8Dar+and+Marko+Robnik%2D%C5%A0ikonja%2E+2021%2E+Training+dataset+and+dictionary+sizes+matter+in+bert+models%3A+the+case+of+baltic+languages%2E+In+International+conference+on+analysis+of+images%2C+social+network)
29. Benjamin Warner, Antoine Chaffin, Benjamin Clavié, Orion Weller, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Griffin Thomas Adams, Jeremy Howard, and Iacopo Poli. 2025. Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory e… [find](https://scholar.google.com/scholar?q=Benjamin+Warner%2C+Antoine+Chaffin%2C+Benjamin+Clavi%C3%A9%2C+Orion+Weller%2C+Oskar+Hallstr%C3%B6m%2C+Said+Taghadouini%2C+Alexis+Gallagher%2C+Raja+Biswas%2C+Faisal+Ladhak%2C+Tom+Aarsen%2C+Griffin+Thomas+Adams%2C+Jeremy+Howard%2C+and+I) [our card](https://md.research.elamur.ai/free/en/papers/warner-2024-smarter-better-faster-longer-modern/)
30. A. Znotins and E. Cirule. 2018. Nlp-pipe: Latvian nlp tool pipeline. In Human Language Technologies - The Baltic Perspective, volume 307, pages 183–189. IOS Press. [find](https://scholar.google.com/scholar?q=A%2E+Znotins+and+E%2E+Cirule%2E+2018%2E+Nlp%2Dpipe%3A+Latvian+nlp+tool+pipeline%2E+In+Human+Language+Technologies+%2D+The+Baltic+Perspective%2C+volume+307%2C+pages+183%E2%80%93189%2E+IOS+Press%2E)
31. Arturs Znotins. 2026. Pretraining and benchmarking modern encoders for latvian. In Proceedings of the Second Workshop on Language Models for Low-Resource Languages. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Arturs+Znotins%2E+2026%2E+Pretraining+and+benchmarking+modern+encoders+for+latvian%2E+In+Proceedings+of+the+Second+Workshop+on+Language+Models+for+Low%2DResource+Languages%2E+Association+for+Computational+Lingu)
32. Arturs Znotins and Guntis Barzdins. 2020. LVBERT: Transformer-Based Model for Latvian Language Understanding. In Human Language Technologies - The Baltic Perspective, volume 328, pages 111–115. IOS Press. 9. [find](https://scholar.google.com/scholar?q=Arturs+Znotins+and+Guntis+Barzdins%2E+2020%2E+LVBERT%3A+Transformer%2DBased+Model+for+Latvian+Language+Understanding%2E+In+Human+Language+Technologies+%2D+The+Baltic+Perspective%2C+volume+328%2C+pages+111%E2%80%93115%2E+IOS+Pr)
33. Language Resource References Auzina, Ilze and Dargis, Roberts and Bojars, Uldis and Paikens, Peteris and Znotins, Arturs and Rabante-Busa, Guna. 2018. Corpus of the Saeima (the Parliament of Latvia). IMCS at University of Latvia. [find](https://scholar.google.com/scholar?q=Language+Resource+References+Auzina%2C+Ilze+and+Dargis%2C+Roberts+and+Bojars%2C+Uldis+and+Paikens%2C+Peteris+and+Znotins%2C+Arturs+and+Rabante%2DBusa%2C+Guna%2E+2018%2E+Corpus+of+the+Saeima+%28the+Parliament+of+Latvia%29%2E+)
34. ‘ Roberts Dar gis. 2022a. Corpus of legal acts of the republic of latvia (likumi). CLARIN-LV digital library at IMCS, University of Latvia. [find](https://scholar.google.com/scholar?q=%E2%80%98+Roberts+Dar+gis%2E+2022a%2E+Corpus+of+legal+acts+of+the+republic+of+latvia+%28likumi%29%2E+CLARIN%2DLV+digital+library+at+IMCS%2C+University+of+Latvia%2E)
35. ‘ Roberts Dar gis. 2022b. Latvian wikipedia. CLARIN-LV digital library at IMCS, University of Latvia. [find](https://scholar.google.com/scholar?q=%E2%80%98+Roberts+Dar+gis%2E+2022b%2E+Latvian+wikipedia%2E+CLARIN%2DLV+digital+library+at+IMCS%2C+University+of+Latvia%2E)
36. ‘ Levāne-Petrova, Kristı̄ne and Dar gis, Roberts and Pokratniece, Kristı̄ne and Lasmanis, Viesturs Jūlijs. 2023. Balanced Corpus of Modern Latvian (LVK2022). ISLRN [http://hdl.handle.net/20.500.12574/84](http://hdl.handle.net/20.500.12574/84). CLARIN-LV digital library at IMCS, University of Latvia. [↗](http://hdl.handle.net/20.500.12574/84)
37. Zeman, Daniel and Nivre, Joakim and Abrams, Mitchell and Ackermann, Elia. 2021. Universal Dependencies 2.17. LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University, ISLRN [http://hdl.handle.net/11234/1-4611](http://hdl.handle.net/11234/1-4611). [↗](http://hdl.handle.net/11234/1-4611)