Elamur Research⌕
☰
home / papers / 2026 / Modular Approach to Automating Morphological Components in Grammar Engineering

Modular Approach to Automating Morphological Components in Grammar Engineering

Paper · 2026 · Ekaterina Voloshina and Krasimir Angelov

Summary

Writing formal grammars by hand is time-consuming and requires native-speaker knowledge of the language. The authors propose a method for automatically building the morphological part of grammars for Grammatical Framework (GF) from inflection examples. The data are taken from Unimorph and Wiktionary. The pipeline consists of three independent modules: first, the paradigm structure is built; then inflectional classes with affix templates are extracted; finally, "smart paradigms" are generated. Such paradigms guess a word's class from a few principal parts. Each module outputs GF code that a linguist can correct before passing it on to the next stage. Knowledge about the language can be added through Python plugins: data cleaning, part-of-speech correction, fixed principal parts. According to the experiments, the automatically inferred rules are not inferior in quality to hand-written grammars. When data are very scarce, prior linguistic knowledge improves the result. The method speeds up grammar development, and the result remains human-readable. This is important for low-resource languages.

Key points

  • The pipeline consists of three modules: paradigm construction, extraction of inflectional classes, and class prediction. A human can intervene after each of them.
  • Data sources: Unimorph and Wiktionary. Language-specific plugins make it possible to filter lemmas and forms, correct parts of speech, and restructure the paradigm tree.
  • As a proof of concept, 7 new languages were added to the GF library. The code is open source: GrammaticalFramework/rgl-learner.
  • Context: the GF library covers more than 40 languages. GF WordNet has lexicons for 264 languages, but morphology and syntax are described for only 45.
  • As an example of generated code, the appendix presents the morphology of Albanian nouns: 16 forms, classes such as mkN006, and a function regN that selects the class based on the word's ending.

In the portion of the text you provided, the middle of the paper is missing. Therefore, the summary contains no specific numbers from the experiments: the results are described only as they are stated in the abstract and the introduction.

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, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 2Research subjects and languages the work is about.Morphology · 405 worksSyntax & grammar formalisms · 214 works

Cite

Cite as Ekaterina Voloshina and Krasimir Angelov. 2026. Modular Approach to Automating Morphological Components in Grammar Engineering. Proceedings of the Fifteenth Language Resources and Evaluation Conference.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/4xy6oka3pbfi

@inproceedings{voloshina2026modular,
  title = {{Modular Approach to Automating Morphological Components in Grammar Engineering}},
  author = {Ekaterina Voloshina and Krasimir Angelov},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/4xy6oka3pbfi},
  url = {https://doi.org/10.63317/4xy6oka3pbfi}
}

References

39 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Malin Ahlberg, Markus Forsberg, and Mans Hulden. 2015. Paradigm classification in supervised learning of morphology. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1024– 1029, Denver, Colorado.… find
  2. Krasimir Angelov. 2024. A scalable database for syntactic and lexical resources. In CLIRAI 2024: Computational Linguistics, Information, Reasoning, and AI. find
  3. Sarah Beemer, Zak Boston, April Bukoski, Daniel Chen, Princess Dickens, Andrew Gerlach, Torin Hopkins, Parth Anand Jawale, Chris Koski, Akanksha Malhotra, Piyush Mishra, Saliha Muradoglu, Lan Sang, Tyler Short, Sagarika Shreev-astava, Elizabeth Spaulding, Testumichi Umada, Beilei Xiang, Changbing Ya… find
  4. Sarah Beemer, Zak Boston, April Bukoski, Daniel Chen, Princess Dickens, Andrew Gerlach, Torin Hopkins, Parth Anand Jawale, Chris Koski, Akanksha Malhotra, et al. 2020b. Linguist vs. machine: Rapid development of finite-state morphological grammars. In Proceedings of the 17th SIGMORPHON Workshop on C… find
  5. Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans Hulden. 2017a. find
  6. CoNLL-SIGMORPHON 2017 shared task: Universal morphological reinflection in 52 languages. In Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, pages 1–30, Vancouver. Association for Computational Linguistics.
  7. Ryan Cotterell, John Sylak-Glassman, and Christo Kirov. 2017b. Neural graphical models over strings for principal parts morphological paradigm completion. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 759… find
  8. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3254–3264, Brussels, Belgium. Association for Computational Linguistics. find
  9. Grégoire Détrez and Aarne Ranta. 2012. Smart paradigms and the predictability and complexity of inflectional morphology. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 645–653, Avignon, France. Association for Computational Lingu… find
  10. Jordan Kodner, Sarah Payne, Salam Khalifa, and Zoey Liu. 2023. Morphological inflection: A reality check. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6082–6101, Toronto, Canada. Association for Computational Linguistics.
  11. A. Doyle. 2001. Irish. Languages of the world: Materials. LINCOM Europa. find
  12. William Burley Lockwood. 1977. An introduction to modern Faroese. Nám. find
  13. Matthew S. Dryer. 2013. Prefixing vs. suffixing in inflectional morphology (v2020.4). In Matthew S. Dryer and Martin Haspelmath, editors, The World Atlas of Language Structures Online. Zenodo. find
  14. Peter Hugoe Matthews. 1972. Inflectional morphology: A theoretical study based on aspects of Latin verb conjugation, volume 6. CUP Archive. find
  15. Jasmine Dum-Tragut. 2009. Armenian. find
  16. Raphael Finkel and Gregory Stump. 2007. Principal parts and morphological typology. Morphology, 17:39–75. find
  17. Victor A Friedman. 2002. Macedonian. Lincom Europa Munich. find
  18. Omer Goldman and Reut Tsarfaty. 2021. Minimal supervision for morphological inflection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2078–2088, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  19. Kristen Howell and Emily M Bender. 2022. Building analyses from syntactic inference in local languages: An HPSG grammar inference system. Northern european journal of language technology, 8. find
  20. Ulrike Janssen and Martina Penke. 2002. How are inflectional affixes organized in the mental lexicon?: Evidence from the investigation of agreement errors in agrammatic aphasics. Brain and Language, 81(1-3):180–191. find
  21. Katharina Kann, Ryan Cotterell, and Hinrich Schütze. 2017. Neural multi-source morphological reinflection. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 514–524, Valencia, Spain. Association for Computatio… find
  22. Katharina Kann and Hinrich Schütze. 2018. Neural transductive learning and beyond: Morphological generation in the minimal-resource setting. find
  23. Aarne Ranta. 2011. Grammatical framework: Programming with multilingual grammars, volume 173. CSLI Publications, Center for the Study of Language and Information Stanford. find
  24. Miikka Silfverberg and Mans Hulden. 2018. An encoder-decoder approach to the paradigm cell filling problem. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2883–2889. find
  25. Miikka Silfverberg, Ling Liu, and Mans Hulden. 2018a. A computational model for the linguistic notion of morphological paradigm. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1615–1626, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  26. Miikka Silfverberg, Ling Liu, and Mans Hulden. 2018b. A computational model for the linguistic notion of morphological paradigm. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1615–1626. find
  27. Miikka Silfverberg, Adam Wiemerslage, Ling Liu, and Lingshuang Jack Mao. 2017. Data augmentation for morphological reinflection. In Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, pages 90–99, Vancouver. Association for Computational Linguistics.
  28. Dávid Somfai Kara. 2002. Kazak (languages of the world/materials 417.). München: LINCOM Europa. find
  29. Ingrid Sonnenstuhl, Meike Hadler, Sonja Eisen-beiss, and Harald Clahsen. 2000. Morphological paradigms in the mental lexicon. In 9th International Morphology Meeting, Vienna. find
  30. Gregory T Stump. 2001. Inflectional morphology: A theory of paradigm structure, volume 93. Cambridge University Press. find
  31. Linda Wiechetek, Flammie Pirinen, Mika Hämäläinen, and Chiara Argese. 2021. Rules ruling neural networks - neural vs. rule-based grammar checking for a low resource language. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1526–153… find
  32. Adam Wiemerslage, Miikka Silfverberg, Changbing Yang, Arya McCarthy, Garrett Nicolai, Eliana Col-unga, and Katharina Kann. 2022. Morphological processing of low-resource languages: Where we are and what‘s next. In Findings of the Association for Computational Linguistics: ACL 2022, pages 988–1007, D… find
  33. Tatu Ylonen. 2022. Wiktextract: Wiktionary as machine-readable structured data. In Proceedings of the 13th Conference on Language Resources and Evaluation, pages 1317–1325. find
  34. Arnold M Zwicky. 1985. How to describe inflection. In Annual Meeting of the Berkeley Linguistics Society, pages 372–386. 11. find
  35. Language Resource References Krasimir Angelov. 2020. A parallel WordNet for English, Swedish and Bulgarian. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3008–3015. find
  36. Krasimir Angelov. 2025. An abstract multilingual WordNet. In Global WordNet Conference 2025. find
  37. Marie-Catherine De Marneffe, Christopher D Manning, Joakim Nivre, and Daniel Zeman. 2021. Universal dependencies. Computational linguistics, 47(2):255–308.
  38. Aarne Ranta. 2009. The GF resource grammar library. Linguistic Issues in Language Technology. find
  39. John Sylak-Glassman. 2016. The composition and use of the universal morphological feature schema (unimorph schema). Johns Hopkins University, page 6. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/voloshina-2026-modular-approach-automating-morphological-components/