Elamur Research⌕
☰
home / papers / 2026 / Slovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation

Slovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation

Summary

Slovene is a highly inflected South Slavic language, but it has had no openly accessible, human-verified data for splitting words into morphemes. Earlier segmentation experiments relied on the BSSJB word-family dictionary, which is not freely available, and its segments were derived automatically without manual checking. The authors fill this gap with the first public, expert-annotated Slovene resource of this kind. It contains 1,935 words taken from Sloleks 3.0, each labelled by two specialists in Slavic word formation.

Every entry has three layers:

  • a fine-grained morphological split that includes inflectional endings,
  • a coarser word-formation split that keeps together the affixes added in one derivational step,
  • the underlying simplex, meaning the non-derived base word.

Both segmentation layers explicitly mark zero-morphemes. A four-stage annotation workflow produced inter-annotator agreement of roughly 85–87% Krippendorff's Alpha. To check that the labels are consistent and learnable, the team trained a segmentation model. It scored higher on morphemes than the earlier Slovene result, despite much less training data. The resource therefore supports reproducible work on Slovene morphology tools.

Key points

  • Dataset size and access: 1,935 Slovene words sourced from Sloleks 3.0, released openly at hdl.handle.net/11356/2060. The authors present it as the first publicly available manually annotated Slovene dataset for this task.
  • Annotation layers: morphological segments, word-formation segments and simplex forms, with ∅-morphemes covering three cases:
    • inflectional, e.g. korak-∅;
    • zero-derivation;
    • compounding boundaries, e.g. tri-∅-kol-es-en-∅.
  • Inter-annotator agreement (Krippendorff's Alpha): 86.80% for morphological segmentation and 85.16% for word-formation segmentation.
  • Model validation (BPR F1): the model achieved 87.78% when splitting words into morphemes and 83.05% for the word-formation layer. This beats the prior Slovene morphological result (Pranjić and Pollak, 2024), which used about 9,883 automatically derived examples from BSSJB.
  • Annotation sources and rules: annotators consulted SSKJ, SP 2001, BSJ and Snoj's etymological dictionary. Explicit rules cover allomorphic stems (dan → dnev-), feminatives, expert nouns derived from field names, hypothetical intermediate words, and compounds.

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

Topics: Morphology

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/4f6rruft238c

@inproceedings{pranjic2026slovene,
  title = {{Slovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation}},
  author = {Pranjić, Marko and Kern, Boris and Voršič, Ines and Pollak, Senja},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/4f6rruft238c},
  url = {https://doi.org/10.63317/4f6rruft238c}
}

References

43 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. find our card
  2. K. Batsuren, O. Goldman, S. Khalifa, N. Habash, W. Kieraś, G. Bella, B. Leonard, G. Nicolai, K. Gorman, Y. G. Ate, M. Ryskina, S. Mielke, E. Budianskaya, C. El-Khaissi, T. Pimentel, M. Gasser, W. A. Lane, M. Raj, M. Coler, J. R. M. Samame, D. S. Camaiteri, E. Z. Rojas, D. López Francis, A. Oncevay,… find our card
  3. Khuyagbaatar Batsuren, Gábor Bella, Aryaman Arora, Viktor Martinovic, Kyle Gorman, Zdeněk Žabokrtský, Amarsanaa Ganbold, Šárka Dohnalová, Magda Ševčíková, Kateřina Pelegrinová, Fausto Giunchiglia, Ryan Cotterell, and Ekaterina Vylomova. 2022b. find
  4. The SIGMORPHON 2022 shared task on morpheme segmentation. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 103–116, Seattle, Washington. Association for Computational Linguistics. find our card
  5. Khuyagbaatar Batsuren, Gábor Bella, and Fausto Giunchiglia. 2021. MorphyNet: a large multilingual database of derivational and inflectional morphology. In Proceedings of the 18th SIGMOR-PHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 39–48, Online. Association… find our card
  6. Jatayu Baxi and Brijesh Bhatt. 2024. Recent advancements in computational morphology : A comprehensive survey. find
  7. Ryan Cotterell, Thomas Müller, Alexander Fraser, and Hinrich Schütze. 2015. Labeled morphological segmentation with semi-Markov models. In Proceedings of the Nineteenth Conference on Computational Natural Language Learning, pages 164–174, Beijing, China. Association for Computational Linguistics. find
  8. Mathias Creutz and Krista Lagus. 2002. Unsupervised discovery of morphemes. In Proceedings of the ACL-02 Workshop on Morphological and Phonological Learning, pages 21–30. find
  9. Mathias Johan Philip Creutz and Krista Hannele Lagus. 2005. Inducing the morphological lexicon of a natural language from unannotated text. In Proc. International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning (AKRR’05), pages 106–113. find
  10. Tomaž Erjavec, Marko Pranjić, Andraž Pelicon, Boris Kern, Irena Stramljič Breznik, and Senja Pollak. 2023. Automating derivational morphology for slovenian. In Electronic lexicography in the 21st century (eLex 2023): Invisible Lexicography. Proceedings of the eLex 2023 conference, pages 449—-465. Le… find
  11. Mario Giulianelli, Marco Del Tredici, and Raquel Fernández. 2020. Analysing lexical semantic change with contextualised word representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3960–3973, Online. Association for Computational Linguistics… find our card
  12. Miika Hämäläinen, Niko Partanen, Jack Rueter, and Kimmo Kohonen. 2021. Neural morphology dataset and models for multiple languages, from the large to the endangered. In Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), pages 166–177, Reykjavik, Iceland (Online). Link… find
  13. Karolína Horenovská. 2019. Extending czech thesauri using word-formation network. In Conference on Theory and Practice of Information Technologies. find
  14. Jue Hou, Anisia Katinskaia, Anh-Duc Vu, and Roman Yangarber. 2023. Effects of sub-word segmentation on performance of transformer language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7413–7425, Singapore. Association for Computational Ling… find
  15. Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991. find our card
  16. Ayyoob ImaniGooghari, Peiqin Lin, Amir Hossein Kargaran, Silvia Severini, Masoud Jalili Sabet, Nora Kassner, Chunlan Ma, Helmut Schmid, André Martins, François Yvon, and Hinrich Schütze. 2023. Glot500: Scaling multilingual corpora and language models to 500 languages. In Proceedings of the 61st Annu… find
  17. Boris Kern. 2017. Stopenjsko besedotvorje. Na primeru glagolov čutnega zaznavanja. Number 11 in Lingua Slovenica. Založba ZRC, Ljubljana. find
  18. Boris Kern. 2024. Considering word formation in compiling dictionaries. In Lexicography and Semantics: proceedings of the XXI EURALEX International Congress, 8-12 October 2024, Cavtat, Croatia, pages 438–448. Institut za hrvatski jezik. find
  19. Klaus Krippendorff. 1970. Estimating the reliability, systematic error and random error of interval data. Educational and Psychological Measurement, 30(1):61–70. find
  20. Mikko Kurimo, Sami Virpioja, Ville Turunen, and Krista Lagus. 2010. Morpho challenge 2005-2010: Evaluations and results. In Proceedings of the 11th Meeting of the ACL Special Interest Group on Computational Morphology and Phonology, pages 87–95, Uppsala, Sweden. Association for Computational Linguis… find
  21. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. In International Conference on Learning Representations. find
  22. Büşra Marşan, Salih Akkurt, Muhammet Şen, Merve Gürbüz, Onur Güngör, Şaziye Özateş, Suzan Uskudarli, Arzucan Özgür, Tunga Gungor, and Balkiz Ozturk. 2022. Enhancements to the boun treebank reflecting the agglutinative nature of turkish. In Proceedings of the 14th International Workshop on Turkish Na… find
  23. Eleni Metheniti and Guenter Neumann. 2020. Wikinflection corpus: A (better) multilingual, morpheme-annotated inflectional corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3905–3912, Marseille, France. European Language Resources Association. find
  24. Tomáš Musil, Jonáš Vidra, and David Mareček. 2019. Derivational morphological relations in word embeddings. In Proceedings of the 2019 find
  25. ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 173– 180, Florence, Italy. Association for Computational Linguistics. find
  26. 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 Twelfth Language Resources and Evalu… find
  27. Marko Pranjić and Senja Pollak. 2024. Razvoj au-tomatske morfološke segmentacije za slovenski jezik = Advancements in automatic morphological segmentation for slovene. In Stopenjsko besedotvorje: 23. mednarodna znanstvena konferenca Komisije za besedotvorje pri Med-narodnem slavističnem komiteju, pa… find
  28. Marko Pranjić, Marko Robnik-Šikonja, and Senja Pollak. 2024. LLMSegm: Surface-level morphological segmentation using large language model. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10665–10674,… find
  29. Magda Sevcíková and Z. Žabokrtský. 2014. Word-formation network for czech. In International Conference on Language Resources and Evaluation. find
  30. Irena Stramljič Breznik. 2004. Besednodružinski slovar slovenskega jezika, Poskusni zvezek za iztočnice na B (Word-family dictionary of Slovenian, Trial volume for headwords beginning with letter B). Slavistično društvo, Maribor. find
  31. Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2818–2826. find
  32. Matej Ulčar and Marko Robnik-Šikonja. 2021. SloBERTa: Slovene monolingual large pre-trained masked language model. In 24th international multiconference Information Society 2021, volume C. Data Mining and Data Warehouses. find
  33. M. Ulčar and M. Robnik-Šikonja. 2020. FinEst BERT and CroSloEngual BERT: less is more in multilingual models. In Text, Speech, and Dialogue TSD 2020, volume 12284 of Lecture Notes in Computer Science. Springer. find
  34. Jonáš Vidra, Zdeněk Žabokrtský, Magda Ševčíková, and Lukáš Kyjánek. 2019. DeriNet 2.0: Towards an all-in-one word-formation resource. In Proceedings of the Second International Workshop on Resources and Tools for Derivational Morphology, pages 81–89, Prague, Czechia. Charles University, Faculty of M… find
  35. Elena Volodina, Yousuf Ali Mohammed, and Therese Lindström Tiedemann. 2021. CoDe-RooMor: A new dataset for non-inflectional morphology studies of Swedish. In Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), pages 178–189, Reykjavik, Iceland (Online). Linköping Unive… find
  36. Zdeněk Žabokrtský, Magda Ševčíková, Milan Straka, Jonáš Vidra, and Adéla Limburská. 2016. Merging data resources for inflectional and derivational morphology in Czech. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 1307–1314, Portorož, Slov… find
  37. Language Resource References A. Bajec, K. Ahačič, M. Bojc, M. Borin, S. Bunc, V. Cestnik, F. Dajnko, M. Furlan, A. Glinšek, A. Gložančev, M. Gradečak, K. Grašič, M. Hajdín, M. Hajnšek-Holz, T. Jarc, F. Jakopin, A. Janežič, M. Kmecl, T. Korošec, Z. Krassnig, L. Legiša, A. Lukan, M. Mejak, M. Miklavči… find
  38. Čibej, Jaka. 2024. Dataset of Slovene word formation trees ArboSloleks 1.0. Slovenian language resource repository CLARIN.SI. find
  39. Čibej, Jaka and Arhar Holdt, Špela and Krek, Simon. 2024. List of word relations from the Sloleks 2.0 lexicon 1.1. Slovenian language resource repository CLARIN.SI. find
  40. Čibej, Jaka and Gantar, Kaja and Dobrovoljc, Kaja and Krek, Simon and Holozan, Peter and Erjavec, Tomaž and Romih, Miro and Arhar Holdt, Špela and Krsnik, Luka and Robnik-Šikonja, Marko. 2022. Morphological lexicon Sloleks 3.0. Slovenian language resource repository CLARIN.SI. find
  41. Janez Dular, Milena Hajnšek-Holz, Franc Jakopin, Janko Moder, Jože Toporišič, Martin Ahlin, Ljudmila Bokal, Alenka Gložančev, Janez Keber, Branka Lazar, Zvonka Praznik, Jerica Snoj, Nastja Vojnovič, Stane Suhadolnik, Peter Weiss, and Vlado Nartnik. 2019. Dictionary of the slovenian normative guide -… find
  42. Ivanka Šircelj-Žnidaršič, Milena Hajnšek-Holz, Polona Kostanjevec, Andreja Žele, Marjeta Humar, Vlado Nartnik, Janez Keber, Borislava Košmrlj-Levačič, and Primož Jakopin. 1998. Besedišče slovenskega jezika z oblikoslovnimi podatki: A - Ž: po gradivu za slovar sodobnega knjižnega jezika zbrane besede… find
  43. Marko Snoj. 2016. Slovenski etimološki slovar, 3. izd. edition. Založba ZRC. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/pranjic-2026-slovene-morphological-word-formation-segmentation/