Elamur Research⌕
☰
home / papers / 2026 / A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora

A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora

Summary

Construction grammars have long been criticized because their precise formal models are hard to scale. The authors propose a way to automatically learn large computational construction grammars from corpora in which sentences carry both syntactic and semantic annotation. For English, the input consists of constituency trees built by the Berkeley Neural Parser (via spaCy) and PropBank roleset annotations from the OntoNotes and English Web Treebank corpora. The algorithm makes a single pass over the corpus. For each roleset instance, it finds the tree nodes that correspond to the roles and builds constructions linked to one another through categories. One of them recognizes words capable of evoking a frame by their lemma and part of speech. Another maps a configuration of constituents onto the core (numbered) roles. The result is networks of tens of thousands of human-interpretable constructions in the Fluid Construction Grammar formalism. They can be used for frame-semantic analysis of open-domain texts and for corpus-based study of argument structure. The work shows that broad coverage can be achieved with shallow generalizations alone, without a formal division into substantive and non-substantive constructions.

Key points

  • Data: the multi-genre English corpora OntoNotes and EWT with exhaustive PropBank annotation. Only core roles (arg0, arg1, arg2…) are taken into account; the method ignores modifiers such as argm-tmp.
  • The construction for a frame-evoking word (for example, tell(verb)) is not tied to a specific roleset. The same construction therefore serves both tell.01 and tell.02, and sense selection takes place later.
  • Resources: the method is integrated into the open-source FCG framework. Released alongside the code are pre-trained grammars for English and PyFCG-compatible scripts for processing new data, training, and linguistic analysis of the grammars (fcg-net.org/fcg-propbank).
  • The grammar was evaluated on semantic role extraction from new texts. The authors present the result as a baseline for a "pure" grammar, without task-specific optimizations.
  • Limitations: the method depends on an external parser, so roles that do not coincide with constituents are lost. It has been applied only to English. Transfer to UD and AMR (important for languages that are not usually analyzed in terms of constituents) is left for future work.

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

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.conll-main.13 · arXiv 2603.12754

@inproceedings{eecke2026method,
  title = {{A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora}},
  author = {Eecke, Paul Van and Beuls, Katrien},
  booktitle = {Proceedings of the 30th Conference on Computational Natural Language Learning},
  year = {2026},
  doi = {10.18653/v1/2026.conll-main.13},
  eprint = {2603.12754},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2026.conll-main.13}
}

References

79 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Afra Alishahi and Suzanne Stevenson. 2008. A computational model of early argument structure acquisition. Cognitive Science, 32(5):789–834. find
  2. Collin Baker, Charles Fillmore, and John Lowe. 1998. The berkeley framenet project. In Proceedings of the 17th international conference on Computational linguistics-Volume 1, pages 86–90. Association for Computational Linguistics. find our card
  3. Fabian Barteld and Alexander Ziem. 2020. Construction mining: Identifying construction candidates for the german constructicon. Belgian Journal of Linguistics, 34(1):5–16. find
  4. Barend Beekhuizen. 2015. Constructions Emerging. Ph.D. thesis, Universiteit Leiden. find
  5. Giulia Bencini and Adele E. Goldberg. 2000. The contribution of argument structure constructions to sentence meaning. Journal of Memory and Language, 43(4):640–651. find
  6. Alexander Bergs. 2018. Because science! notes on a variable. Subordination in English: Synchronic and diachronic perspectives, 101:43. find
  7. Katrien Beuls and Paul Van Eecke. 2023. Fluid Construction Grammar: State of the art and future outlook. In Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+NLP, GURT/SyntaxFest 2023), pages 41–50. Association for Computational Linguistics. find our card
  8. Katrien Beuls and Paul Van Eecke. 2024. Humans learn language from situated communicative interactions. What about machines? Computational Linguistics, 50(4):1277–1311. find
  9. Katrien Beuls, Paul Van Eecke, and Vanja Sophie Can-galovic. 2021. A computational construction grammar approach to semantic frame extraction. Linguistics Vanguard, 7(1):20180015. find
  10. Ann Bies, Justin Mott, Colin Warner, and Seth Kulick. 2012. English web treebank ldc2012t13. Philadelphia, Linguistic Data Consortium. find
  11. Hans C. Boas. 2025. Constructional syntax. In Mirjam Fried and Kiki Nikiforidou, editors, The Cambridge Handbook of Construction Grammar, pages 44–70. Cambridge University Press, Cambridge, United Kingdom. find
  12. Rens Bod. 2009. Constructions at work or at rest? Cognitive Linguistics, 20(1):129–134. find
  13. Sasha Boguraev, Christopher Potts, and Kyle Mahowald. 2025. Causal interventions reveal shared structure across English filler–gap constructions. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 25032–25053. find our card
  14. Claire Bonial, Bianca Badarau, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Tim O’Gorman, Martha Palmer, and Nathan Schneider. 2018. Abstract meaning representation of constructions: The more we include, the better the representation. In Proceedings of the Eleventh International Conference on Languag… find
  15. Claire Bonial, Claire Benet Post, Paul Van Eecke, Katrien Beuls, and Harish Tayyar Madabushi. 2026. CxGr-AMR: Extending abstract meaning representation beyond lexically anchored relations with constructional rolesets. In Proceedings of The Seventh International Workshop on Designing Meaning Represen… find
  16. Claire Bonial and Harish Tayyar Madabushi. 2024. Constructing understanding: on the constructional information encoded in large language models. Language Resources and Evaluation. find
  17. Nancy Chang. 2008. Constructing grammar: A computational model of the emergence of early constructions. Ph.D. thesis, University of California, Berkeley, Berkeley, CA, USA. find
  18. William Croft. 2001. Radical construction grammar: Syntactic theory in typological perspective. Oxford University Press, Oxford, United Kingdom. find
  19. Holger Diessel. 2015. Usage-based construction grammar. In Ewa Dabrowska and Dagmar Divjak, editors, Handbook of Cognitive Linguistics, pages 295–321. De Gruyter Mouton, Berlin, Germany. find
  20. Ellen Dodge, Sean Trott, Luca Gilardi, and Elise Stickles. 2017. Grammar scaling: Leveraging FrameNet data to increase embodied construction grammar coverage. In The 2017 AAAI Spring Symposium Series, pages 154–162, Washington, DC, USA. AAAI Press. find
  21. Jonas Doumen, Katrien Beuls, and Paul Van Eecke. 2024. Modelling constructivist language acquisition through syntactico-semantic pattern finding. Royal Society Open Science, 11(7):231998. find
  22. Jonas Doumen, Veronica J. Schmalz, Katrien Beuls, and Paul Van Eecke. 2025. The computational learning of construction grammars: State of the art and prospective roadmap. Constructions and Frames, 17(1):141–174. find
  23. Jonathan Dunn. 2017. Computational learning of construction grammars. Language and Cognition, 9(2):254–292. find
  24. Jonathan Dunn. 2022. Exposure and emergence in usage-based grammar: Computational experiments in 35 languages. Cognitive Linguistics, 33(4):659– 699. find
  25. Charles J. Fillmore. 1976. Frame semantics and the nature of language. In Annals of the New York Academy of Sciences: Conference on the origin and development of language and speech, volume 280 (1), pages 20–32. find
  26. Charles J. Fillmore. 1988. The mechanisms of “construction grammar”. In Proceedings of the Fourteenth Annual Meeting of the Berkeley Linguistics Society, volume 14, pages 35–55. Linguistic Society of America. find
  27. Charles J. Fillmore, Paul Kay, and Mary Catherine O’Connor. 1988. Regularity and idiomaticity in grammatical constructions: The case of let alone. Language, 64(3):501–538. find
  28. Charles J. Fillmore, Russell R. Lee-Goldman, and Russell Rhodes. 2012. The FrameNet constructicon. In Hans C. Boas and Ivan A. Sag, editors, Sign-based construction grammar, pages 309–372. CSLI Publications/Center for the Study of Language and Information, Stanford, CA, USA. find
  29. Markus Forsberg, Richard Johansson, Linnéa Bäckström, Lars Borin, Benjamin Lyngfelt, Joel Olofs-son, and Julia Prentice. 2014. From construction candidates to constructicon entries: An experiment using semi-automatic methods for identifying constructions in corpora. Constructions and Frames, 6(1):11… find
  30. Mirjam Fried. 2015. Construction grammar. In Tibor Kiss and Artemis Alexiadou, editors, Syntax – Theory and Analysis: An International Handbook, pages 974–1003. De Gruyter Mouton, Berlin, Germany. find
  31. Mirjam Fried and Kiki Nikiforidou, editors. 2025. The Cambridge Handbook of Construction Grammar. Cambridge University Press, Cambridge, United Kingdom. find
  32. Mirjam Fried and Jan-Ola Östman. 2004. Construction grammar: A thumbnail sketch. In Jan-Ola Östman and Mirjam Fried, editors, Construction grammar in a cross-language perspective, pages 1–86. John Benjamins, Amsterdam, Netherlands. find
  33. Kateryna Gerasymova and Michael Spranger. 2010. Acquisition of grammar in autonomous artificial systems. In Proceedings of the 19th European Conference on Artificial Intelligence (ECAI-2010), pages 923–928, Amsterdam, Netherlands. IOS Press. find
  34. Adele E. Goldberg. 1995. Constructions: A construction grammar approach to argument structure. University of Chicago Press, Chicago, IL, USA. find
  35. Adele E. Goldberg. 2003. Constructions: A new theoretical approach to language. Trends in Cognitive Sciences, 7(5):219–224. find
  36. Adele E. Goldberg. 2019. Explain me this. Princeton University Press, Princeton, NJ, USA. find
  37. Adele E. Goldberg and Ray Jackendoff. 2004. The English resultative as a family of constructions. Language, 80(3):532–568. find
  38. Lars Borin, Kyoko Ohara, and Tiago T. Torrent, editors, Constructicography: Constructicon development across languages, pages 41–106. John Benjamins, Amsterdam, Netherlands. find
  39. Thomas Herbst and Thomas Hoffmann. 2024. A Construction Grammar of the English Language: CASA - a Constructionist Approach to Syntactic Analysis. John Benjamins Publishing Company, Amsterdam/Philadelphia. find
  40. Benjamin Lyngfelt, Lars Borin, Kyoko Ohara, and Tiago T. Torrent, editors. 2018b. Constructicography: Constructicon Development across Languages. John Benjamins, Amsterdam, Netherlands. find
  41. Martin Hilpert. 2014. Construction grammar and its application to English. Edinburgh University Press, Edinburgh, United Kingdom. find
  42. Kirsten Malmkjaer, editor. 2004. The Linguistics Encyclopedia. Routledge, London/New York. Second Edition. find
  43. Martin Hilpert and Samuel Bourgeois. 2020. Inter-subjectification in constructional change: From confrontation to solidarity in the sarcastic much? construction. Constructions and Frames, 12(1):96–120. find
  44. Vanessa Micelli, Joachim De Beule, and Remi van Trijp. 2009. Framing Fluid Construction Grammar. In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 31, pages 3023–3027. Cognitive Science Society. find
  45. Thomas Hoffmann. 2022. Construction Grammar. Cambridge University Press, Cambridge, United Kingdom. find
  46. Ray Jackendoff. 1997. Twistin’ the night away. Language, 73(3):534–559. find
  47. Laura A. Janda, Anna Endresen, Valentina Zhukova, Daria Mordashova, and Ekaterina Rakhilina. 2020. How to build a constructicon in five years: the Russian example. Belgian Journal of Linguistics, 34(1):161–173. find
  48. Paul Kay and Charles Fillmore. 1999. Grammatical constructions and linguistic generalizations: The What’s X Doing Y? construction. Language, 75(1):1–33. find
  49. Nikita Kitaev and Dan Klein. 2018. Constituency parsing with a self-attentive encoder. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 2676–2686. find our card
  50. Andras Kornai. 2008. Mathematical Linguistics. Springer, London, United Kingdom. find
  51. Ronald Langacker. 1987. Foundations of cognitive grammar: Theoretical prerequisites, volume 1. Stanford University Press, Stanford, CA, USA. find
  52. Ronald Langacker. 2003. Constructions in cognitive grammar. English Linguistics, 20(1):41–83. find
  53. Ronald Langacker. 2008. Cognitive Grammar: A Basic Introduction. Oxford University Press, New York, NY, USA. find
  54. Adrieli Laviola, Ludmila Lage, Natalia Marcao, Tatiane Tavares, Vania Almeida, Ely Matos, and Tiago Torrent. 2017. The brazilian portuguese constructicon: Modeling constructional inheritance, frame evocation and constraints in framenet brasil. In The 2017 AAAI Spring Symposium Series, pages 193–196,… find
  55. Benjamin Lyngfelt, Linnea Backstrom, Lars Borin, Anna Ehrlemark, and Rudolf Rydstedt. 2018a. Constructicography at work: Theory meets practice in the swedish constructicon. In Benjamin Lyngfelt, Laura A. Michaelis. 2012. Making the case for construction grammar. In Hans C. Boas and Ivan A. Sag, edit… find
  56. Marvin Minsky. 1974. A framework for representing knowledge. Technical report, Technical Report 306, MIT AI Laboratory, Cambridge, MA, USA. find
  57. Jens Nevens, Jonas Doumen, Paul Van Eecke, and Katrien Beuls. 2022. Language acquisition through intention reading and pattern finding. In Proceedings of the 29th International Conference on Computational Linguistics, pages 15–25. International Committee on Computational Linguistics. find
  58. Kyoko Ohara. 2018. Relations between frames and constructions: A proposal from the japanese framenet constructicon. In Benjamin Lyngfelt, Lars Borin, Kyoko Ohara, and Tiago T. Torrent, editors, Constructicography: Constructicon development across languages, pages 141–164. John Benjamins, Amsterdam,… find
  59. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71– 106. find our card
  60. Steven T. Piantadosi. 2014. Zipf’s word frequency law in natural language: A critical review and future directions. Psychonomic bulletin & review, 21(5):1112– 1130. find
  61. Sameer Pradhan, Julia Bonn, Skatje Myers, Kathryn Conger, Tim O’gorman, James Gung, Kristin Wright-bettner, and Martha Palmer. 2022. PropBank comes of Age—Larger, smarter, and more diverse. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 278–288. find our card
  62. Roger C. Schank and Robert P. Abelson. 1977. Scripts, plans, goals, and understanding: An inquiry into human knowledge structures. Lawrence Erlbaum Associates, Hillsdale, NJ, USA. find
  63. Michael Spranger and Luc Steels. 2015. Co-acquisition of syntax and semantics: an investigation in spatial language. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, pages 1909–1915, Washington, DC, USA. AAAI Press. find
  64. Luc Steels. 2004. Constructivist development of grounded construction grammar. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04), pages 9–16. ACL. find our card
  65. Levin, Amir Zeldes, Joakim Nivre, William Croft, and Nathan Schneider. 2024. UCxn: Typologically informed annotation of constructions atop Universal Dependencies. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 20… find
  66. Anatol Stefanowitsch and Stefan Th Gries. 2003. Col-lostructions: Investigating the interaction of words and constructions. International Journal of Corpus Linguistics, 8(2):209–243. find
  67. Leonie Weissweiler, Valentin Hofmann, Abdullatif Köksal, and Hinrich Schütze. 2022. The better your syntax, the better your semantics? Probing pretrained language models for the English comparative correlative. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing… find
  68. Harish Tayyar Madabushi, Laurence Romain, Dagmar Divjak, and Petar Milin. 2020. CxGBERT: BERT meets construction grammar. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4020–4032. International Committee on Computational Linguistics. find our card
  69. David Wible and Nai-Lung Tsao. 2010. StringNet as a computational resource for discovering and investigating linguistic constructions. In Proceedings of the NAACL HLT Workshop on Extracting and Using Constructions in Computational Linguistics, pages 25–31. find
  70. Michael Tomasello. 2003. Constructing a Language: A Usage-Based Theory of Language Acquisition. Harvard University Press, Harvard, MA, USA. find
  71. Alexander Ziem, Johanna Flick, and Phillip Sand-kühler. 2019. The German constructicon project: Framework, methodology, resources. Lexicographica, 35(2019):15–40. find
  72. Paul Van Eecke and Katrien Beuls. 2025. PyFCG: Fluid Construction Grammar in Python. arXiv preprint arXiv:2505.12920. find
  73. George Kingsley Zipf. 1936. The Psychobiology of Language. Routledge, London, United Kingdom. find
  74. Paul Van Eecke, Jens Nevens, and Katrien Beuls. 2022. Neural heuristics for scaling constructional language processing. Journal of Language Modelling, 10(2):287–314. find
  75. Remi van Trijp. 2017. A computational construction grammar for English. In The 2017 AAAI Spring Symposium Series, pages 266–273, Washington, DC, USA. AAAI Press. find
  76. Remi van Trijp, Katrien Beuls, and Paul Van Eecke. 2022. The FCG Editor: An innovative environment for engineering computational construction grammars. PLOS ONE, 17(6):e0269708. find
  77. Lara Verheyen, Jonas Doumen, Paul Van Eecke, and Katrien Beuls. 2025. You shall know a construction by the company it keeps: Computational construction grammar with embeddings. In Proceedings of the Second International Workshop on Construction Grammars and NLP, pages 75–83. Association for Computat… find our card
  78. Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, and Ann Houston. 2013. Ontonotes release 5.0 ldc2013t19. Philadelphia, Linguistic Data Consortium. find
  79. Leonie Weissweiler, Nina Böbel, Kirian Guiller, Santiago Herrera, Wesley Scivetti, Arthur Lorenzi, Nurit Melnik, Archna Bhatia, Hinrich Schütze, Lori George Kingsley Zipf. 1949. Human Behavior and the Principle of Least Effort. Addison-Wesley, New York, NY, USA. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/eecke-2026-method-learning-large-scale-computational/