Elamur Research⌕
☰
home / papers / 2026 / MesoTree: Annotated Linguistic Resources for Quantitative Comparative Linguistic Analysis and NLP in Mesoamerica

MesoTree: Annotated Linguistic Resources for Quantitative Comparative Linguistic Analysis and NLP in Mesoamerica

Summary

Documentation of Mesoamerican languages is scattered across grammars and small single-language corpora. Each uses its own glossing conventions, which makes it slow to search for phenomena, count them, or compare them across languages. MesoTree addresses this by building Universal Dependencies treebanks for four genetically unrelated Mesoamerican languages: Tepeuxila Cuicatec, San Mateo del Mar Huave, Nahuatl and Uspanteko. Seri, spoken in Sonora just outside the area, is added as a control. The team annotates both previously published material and newly produced texts. The texts deliberately cover three genres (dictionary and grammar examples, edited prose, spontaneous speech) so that the corpora reflect a broad range of morphosyntax. The paper presents the languages, the annotator training and annotation workflow, and the current state of the corpora. To show the resources are useful, the authors run a quantitative comparison of word-order variability across Mesoamerican treebanks and train UD parsers on the new data. The work supports areal typology of the Mesoamerican Sprachbund and gives an underrepresented language group a basis for NLP tools.

Key points

  • The languages covered are Cuicatec (cux), Huave (huv), Nahuatl, Uspanteko (usp) and Seri (sei, the control language). Before this project, the only UD treebanks for Mexican languages were two Nahuatl varieties. The first Mesoamerican UD treebank was K'iche', at roughly 10,000 tokens.
  • A language-specific feature, NounType=Relat, encodes Mesoamerican relational nouns. Morpheme segmentation and glosses are kept in the MSeg and MGloss fields, so interlinear-gloss information is preserved alongside the dependency trees.
  • For the comparative experiment, Shannon entropy of where subjects and objects appear, H(O), H(S) and H(S,O), is measured across 8 treebanks, identified by the codes usp, sei, quc, nhi, huv, cux, cak and azz.
  • In that experiment, Seri shows zero entropy for both subject and object position, consistent with rigid word order. Uspanteko has the highest joint entropy, with H(S,O) = 1.74.
  • For context, UD currently comprises 339 treebanks for 186 languages. The new MesoTree data is also used to train UD parsing models.

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: Universal Dependencies · Treebanks

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/2xvtti733shi

@inproceedings{pugh2026mesotree,
  title = {{MesoTree: Annotated Linguistic Resources for Quantitative Comparative Linguistic Analysis and NLP in Mesoamerica}},
  author = {Pugh, Robert and Tyers, Francis and Henderson, Robert},
  booktitle = {Proceedings of the Ninth Workshop on Universal Dependencies (UDW 2026)},
  year = {2026},
  doi = {10.63317/2xvtti733shi},
  url = {https://doi.org/10.63317/2xvtti733shi}
}

References

55 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Judith Aissen, Nora C England, and Roberto Zavala Maldonado. 2017. The Mayan languages. Taylor & Francis. find
  2. Peter K. Austin. 2021. Language Documentation and Language Revitalization, page 199–219. Cambridge University Press. find
  3. Matthew Baerman. 2016. Seri verb classes: Morphosyntactic motivation and morphological autonomy. Language, 92(4):792–823. find
  4. Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa, Nizar Habash, Witold Kieraś, Gábor Bella, Brian Leonard, Garrett Nicolai, Kyle Gorman, Yustinus Ghanggo Ate, et al. 2022. Uni-Morph 4.0: universal morphology. arXiv preprint arXiv:2205.03608. find our card
  5. Francisco Belmar. 1902. El Cuicateco-Primera Edición. find
  6. Ryan Bennett, Jessica Coon, and Robert Henderson. 2016. Introduction to Mayan linguistics. Language and Linguistics Compass, 10(10):455– 468. find
  7. Andrea L. Berez-Kroeker, Shirley Gabber, and Aliya Slayton. 2023. Recent advances in technologies for resource creation and mobilization in language documentation. Annual Review of Linguistics, 9(1):195–214. find
  8. David P Bradley. 1991. A preliminary syntactic sketch of Concepción Pápalo Cuicatec. Studies in the syntax of Mixtecan languages, 3:409–506. find
  9. Earl Brockway, editor. 1984. Frases en mejicano y español: En el idioma náhuatl de San Miguel de Tenango, Puebla y en español, primera edición edition. Instituto Lingüístico de Verano, A.C., Mexico. find
  10. Cecil Brown. 2011. The Role of Nahuatl in the Formation of Mesoamerica as a Linguistic Area. Language Dynamics and Change, 1:171–204. find
  11. Lyle Campbell, Terrence Kaufman, and Thomas C Smith-Stark. 1986. Meso-america as a linguistic area. Language, pages 530–570. find
  12. Telma Angelina Can Pixabaj. 2007. Gramática uspanteka. Cholsamaj Fundacion. find
  13. Hilaria Cruz, Antonios Anastasopoulos, and Gregory Stump. 2020. A resource for studying chatino verbal morphology. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2827–2831, Marseille, France. European Language Resources Association. find
  14. Marjorie Davis and Margaret Walker. 1955. Cuicateco: Morphemics and morphophonemics. International Journal of American Linguistics, 21(1):46–51. find
  15. Leonel Figueiredo de Alencar. 2024. A Universal Dependencies treebank for nheengatu. In Proceedings of the 16th International Conference on Computational Processing of Portuguese -Vol. 2, pages 37–54, Santiago de Compostela, Galicia/Spain. Association for Computational Lingustics. find our card
  16. Marie-Catherine de Marneffe, Christopher D. Manning, Joakim Nivre, and Daniel Zeman. 2021. Universal dependencies. Computational Linguistics, 47(2):255–308. find our card
  17. Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 2018. AllenNLP: A Deep Semantic Natural Language Processing Platform. In Proceedings of Workshop for NLP Open Source Software (NLP-OSS), pages 1–6, Melbourne,… find our card
  18. Gaël Guibon, Marine Courtin, Kim Gerdes, and Bruno Guillaume. 2020. When collaborative treebank curation meets graph grammars. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5291–5300, Marseille, France. European Language Resources Association. find
  19. Miguel Angel Vicente Méndez. 2007. Cholaj Tzijb’al li Uspanteko: Diccionario bilingüe uspanteko-español. Cholsamaj. find
  20. Bruno Guillaume. 2021. Graph Matching and Graph Rewriting: GREW tools for corpus exploration, maintenance and conversion. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 168– 175. find
  21. Mary B. Moser and Stephen A. Marlett. 2010. Com-caac quih yaza quih hant ihiip hac: Diccionario seri-español-inglés, 2nd edition. Plaza y Valdes editores and Universidad de Sonora. find
  22. Samuel Herrera Castro. 2010. Alineamiento y frase verbal en Huave de San Mateo Del Mar, Oaxaca. Master’s thesis, Escuela Nacional de Antropología e Historia, México, D.F. find
  23. Samuel Herrera Castro. 2016. Sintaxis y semántica de la frase nominal en Huave de San Mateo Del Mar, Oaxaca. Ph.D. thesis, Colegio de México, México, D.F. find
  24. INALI. 2009. Catálogo de las lenguas indígenas nacionales: Variantes lingüísticas de México con sus autodenominaciones y referencias geoes-tadísticas. Instituto Nacional de Lenguas Indigenas, México, D.F. find
  25. Jessica Karson and Rolando Coto-Solano. 2024. Morphological tagging in Bribri using Universal Dependency features. In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), pages 56–66, Mexico City, Mexico. Association for Computat… find
  26. Paul Kirchhoff. 1952. Mesoamerica: its geographic limits, ethnic composition and cultural characteristics. Heritage of conquest, pages 17–30. find
  27. Angelika Kiss and Guillaume Thomas. 2019. Word order variation in Mbyá Guaraní. In Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019), pages 121–129. find
  28. Natalia Levshina. 2019. Token-based typology and word order entropy: A study based on Universal Dependencies. Linguistic Typology, 23(3):533– 572. find
  29. Stephen A. Marlett. 2007. Las relaciones entre las lenguas “hokanas” en México: ¿cuál es la evidencia? Memorias del III Coloquio Internacional de Lingüística Mauricio Swadesh, pages 165–192. find
  30. Stephen A Marlett. 2016. Cmiique Iitom: the Seri language. Unpublished grammar (2016 draft). find
  31. Ruslan Mitkov. 2022. The Oxford Handbook of Computational Linguistics. Oxford University Press. find
  32. Joybrato Mukherjee. 2006. Corpus linguistics and language pedagogy: The state of the art–and beyond. Corpus technology and language pedagogy: New resources, new tools, new methods, pages 5–24. find
  33. Pamela Munro. 2017. The Mesoamerican linguistic area revisited. Language contact and change in Mesoamerica and beyond, pages 335–351. find
  34. Matías Guzmán Naranjo and Laura Becker. 2018. Quantitative word order typology with UD. In Proceedings of the 17th International Workshop on Treebanks and Linguistic Theories (TLT 2018), December 13–14, 2018, Oslo University, Norway, 155, pages 91–104. Linköping University Electronic Press. find
  35. J. Nivre, M.-C. de Marneffe, F. Ginter, J. Hajič, C. D. Manning, S. Pyysalo, S. Schuster, F. Tyers, and D. Zeman. 2020. Universal dependencies v2: An evergrowing multilingual treebank collection. In Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 4027–4036. find
  36. Alexis Mary Palmer. 2009. Semi-automated annotation and active learning for language documentation. find
  37. Robert Pugh, Marivel Huerta Mendez, Mitsuya Sasaki, and Francis Tyers. 2022. Universal dependencies for Western Sierra Puebla Nahuatl. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5011–5020. find
  38. Robert Pugh, Francis Tyers, and Marivel Huerta Mendez. 2021. Towards an open source finite-state morphological analyzer for Zacatlán-Ahuacatlán-Tepetzintla Nahuatl. In Proceedings of the 4th Workshop on the Use of Computational Methods in the Study of Endangered Languages Volume 1 (Papers), pages 80… find
  39. Robert Pugh and Francis M. Tyers. 2024. A Universal Dependencies Treebank for Highland Puebla Nahuatl. In 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics. find
  40. Robert Pugh, Cheyenne Wing, María Ximena Juárez Huerta, Ángeles Márquez Hernandez, and Francis Tyers. 2025. Ihquin tlahtouah in tetelahtzincocah: An annotated, multi-purpose audio and text corpus of western sierra Puebla Nahuatl. In Proceedings of the 2025 Conference of the Nations of the Americas C… find
  41. Michael Richards and Narciso Cojtí Macario. 2003. Atlas lingüístico de Guatemala. Editorial Serviprensa Guatemala City. find
  42. Marcela San Giacomo Trinidad. 2017. The phonetics and phonology of tone in San Juan Tepeuxila Cuicatec. Cuadernos de Lingüística de El Colegio de México, 4(2):83–136. find
  43. Mitsuya Sasaki. 2014. A dialectological sketch of Ixquihuacan Nahuatl. Tokyo University Linguistic Papers, 35:e139–170. tool for universal dependencies. In Proceedings of the 16th international workshop on treebanks and linguistic theories, pages 10–17. find
  44. Francis M. Tyers and Samuel Herrera Castro. 2023. Towards a finite-state morphological analyser for San Mateo Huave. In Proceedings of the 6th Workshop on Computational Methods for Endangered Languages. [to appear]. find
  45. Juan Antonio Us Maldonado. 2009. Monografía Uspanteka. Comunidad Lingüística Uspanteka, San Miguel Uspantán. find
  46. Rob van der Goot, Ahmet Üstün, Alan Ramponi, Ibrahim Sharaf, and Barbara Plank. 2021. Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task learning in NLP. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations… find
  47. Irene Yi, Amelia Lake, Juhyae Kim, Kassandra Haakman, Jeremiah Jewell, Sarah Babinski, and Claire Bowern. 2022. Accessibility, discoverability, and functionality: An audit of and recommendations for digital language archives. Journal of Open Humanities Data. find
  48. Mitsuya Sasaki. 2021. Configurationality in Ixquihuacan Nahuatl. Ph.D. thesis, University of Tokyo. find
  49. Emily F. Stairs and Elena E. de Hollenbach. 1981. Gramática huave. In Glenn A. Stairs Kreger and Emily F. Scharfe de Stairs, editors, Diccionario huave de San Mateo del Mar, pages 283–391. Instituto Lingüístico de Verano, México, D. F. find
  50. A. The entropy calculations for the 8 treebanks (seven for Mesoamerican languages and one Mesoamerica-adjacent) can be seen in Tabl 3. find
  51. Glen Stairs and Emily Stairs. 1981. Diccionario huave de San Mateo del Mar. Instituto Lingüístico de Verano, México, D.F. find
  52. 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. find our card
  53. Guillaume Thomas. 2019. Universal dependencies for Mbyá Guaraní. In Proceedings of the third workshop on universal dependencies (udw, syntaxfest 2019), pages 70–77. find
  54. Shannon’s Entropy Language H(O) H(S) H(S,O) azz cak cux huv nhi quc sei usp 0.81 0.48 0.32 0.32 0.61 0.44 0.0 0.42 0.68 0.95 1.00 1.00 0.89 0.98 0.0 0.90 1.01 1.35 0.96 1.35 0.79 1.31 0.44 1.74 *Table 3: Entropy calculations for the 8 treebanks (seven for Mesoamerican languages and one Mesoamerica-a… find
  55. Francis Tyers, Mariya Sheyanova, and Jonathan Washington. 2017. UD Annotatrix: An annotation find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/pugh-2026-mesotree-annotated-linguistic-resources-quantitative/