Elamur Research⌕
☰
home / papers / 2023 / Yauti: A Tool for Morphosyntactic Analysis of Nheengatu within the Universal Dependencies Framework

Yauti: A Tool for Morphosyntactic Analysis of Nheengatu within the Universal Dependencies Framework

Summary

The paper describes Yauti, a rule-based tool for morphosyntactic analysis of Nheengatu. Nheengatu is an endangered Indigenous language of Brazil with almost no digital resources. Yauti produces annotation in CoNLL-U format following the UD scheme. The tool was developed together with the UD Nheengatu-CompLin treebank and allowed the corpus to grow quickly. It is built on a JSON glossary compiled from the dictionaries of Navarro and Ávila. A morphological generator builds a full-form lexicon from this glossary. The system then splits tokens into syntactic words, including clitics and compound forms, and fills in UPOS and FEATS. It assigns heads and syntactic relations using heuristics based on typical Nheengatu word order. The evaluation was kept separate from unknown-word recognition and disambiguation, so XPOS tags were given in advance. On the treebank, the tool achieved a LAS of 73.2%, and tokenization, lemmas and features are nearly perfect. The author argues that Yauti is also useful for checking the consistency of existing annotation. The paper helps narrow the digital divide for minority languages.

Key points

  • On all 1022 sentences of the UDTB, Yauti achieved a UAS of 80.0 and a LAS of 73.2. This is comparable to the results of UDPipe 2.0 on some treebanks from CoNLL 2018, such as Galician-TreeGal. Tokenization reached 100%, lemmas 99.7%, features about 98.5%, and the SpaceAfter attribute 99.5%.
  • On the unseen text MYTH (43 sentences, 580 tokens, an 1876 myth with modernized spelling), the results were LAS 71.0, UAS 76.3, lemmas 96.6%, features 96.8%.
  • With the tool's help, UD Nheengatu-CompLin grew from 196 sentences in v2.11 to 860 in v2.12. The development version already has 1022 sentences. It is the second-largest treebank of a Brazilian Indigenous language in UD.
  • The glossary has 1552 entries, and the XPOS tagset has 83 tags, including 20 types of particles and 22 subclasses of adverbs.
  • The hardest cases are distinguishing pronouns from determiners and auxiliary verbs from main verbs, as well as sentences with verb–subject order, verbless sentences and iobj. The code is open source: github.com/CompLin/nheengatu.

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

Cited by

2 papers of our library cite it (of the 140673 whose bibliographies we read); each has a page here.

Cite

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

@inproceedings{alencar2023yauti,
  title = {{Yauti: A Tool for Morphosyntactic Analysis of Nheengatu within the Universal Dependencies Framework}},
  author = {Alencar, Leonel Figueiredo de},
  booktitle = {Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology},
  year = {2023},
  doi = {10.5753/stil.2023.234131},
  url = {https://doi.org/10.5753/stil.2023.234131}
}

References

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

  1. Alexandre, D. M., Gurgel, J. L., and de A. Araripe, L. F. (2021a). Compilação de um corpus etiquetado da Lı́ngua Geral Amazônica. In Anais do XIII Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana, pages 427–431, Porto Alegre, RS, Brasil. SBC. find
  2. Alexandre, D. M., Gurgel, J. L., and de Alencar Araripe, L. F. (2021b). Nheentiqueta-dor: Um etiquetador morfossintático para o sintagma nominal do nheengatu. Revista Encontros Universitários da UFC, 6:1–13. find
  3. Avila, M. T. (2021). Proposta de dicionário nheengatu-português. PhD thesis, Faculdade de Filosofia, Letras e Ciências Humanas da Universidade de São Paulo. find
  4. Bapna, A., Caswell, I., Kreutzer, J., Firat, O., van Esch, D., Siddhant, A., Niu, M., Bal-jekar, P., Garcia, X., Macherey, W., Breiner, T., Axelrod, V., Riesa, J., Cao, Y., Chen, M. X., Macherey, K., Krikun, M., Wang, P., Gutkin, A., Shah, A., Huang, Y., Chen, Z., Wu, Y., and Hughes, M. (2022). Buil… find
  5. LOT, Utrecht. da Silva Facundes, S., de Freitas, M. F. P., and de Lima-Padovani, B. F. S. (2021). Number expression in Apurinã (Arawák). In Hämäläinen, M., Partanen, N., and Alnajjar, K., editors, Multilingual Facilitation, pages 31–42. University of Helsinki Library, Helsinki. de Alencar, L. F… find
  6. Typographia da Reforma, Rio de Janeiro. de Marneffe, M.-C., Manning, C. D., Nivre, J., and Zeman, D. (2021). Universal Dependencies. Computational Linguistics, 47(2):255–308. find our card
  7. Eberhard, D. M., Simons, G. F., and Fennig, C. D., editors (2023). Ethnologue: Languages of the World. SIL International, Dallas, twenty-sixth edition. find
  8. Freire, J. R. B. (2011). Rio Babel: A história das lı́nguas na Amazônia. EdUERJ, Rio de Janeiro, second edition. find
  9. Galves, C., Sandalo, F., Sena, T. A. d., and Veronesi, L. (2017). Annotating a polysynthetic language: From Portuguese to Kadiwéu. Cadernos de Estudos Linguı́sticos, 59(3):631–648. find
  10. Gerardi, F. F., Reichert, S., and Aragon, C. C. (2021). TuLeD (tupı́an lexical database): introducing a database of a South American language family. Language Resources and Evaluation, 55(4):997–1015. find
  11. Martı́n Rodrı́guez, L., Merzhevich, T., Silva, W., Tresoldi, T., Aragon, C., and Gerardi, F. F. (2022). Tupı́an language ressources: Data, tools, analyses. In Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages, pages 48–58, Marseille, France. E… find
  12. Moore, D. (2014). Historical development of Nheengatu (Lı́ngua Geral Amazônica). In Mufwene, S. S., editor, Iberian Imperialism and Language Evolution in Latin America, pages 108–142. University of Chicago Press, Chicago. find
  13. Moore, D., Facundes, S., and Pires, N. (1994). Nheengatu (Lı́ngua Geral Amazônica), its history, and the effects of language contact. In Proceedings of the Meeting of the Society for the Study of the Indigenous languages of the Americas, July 2-4, 1993 and the Hokan-Penutian workshop, July 3, 1993,… find
  14. Navarro, E., Ávila, M., and Trevisan, R. (2017). O nheengatu, entre a vida e a morte: A tradução literária como possı́vel instrumento de sua revitalização lexical. Revista Letras Raras, 6(2):9–29. find
  15. Nivre, J., de Marneffe, M.-C., Ginter, F., Goldberg, Y., Hajič, J., Manning, C. D., Mc-Donald, R., Petrov, S., Pyysalo, S., Silveira, N., Tsarfaty, R., and Zeman, D. (2016). Universal Dependencies v1: A multilingual treebank collection. In Proceedings of the Tenth International Conference on Langua… find our card
  16. Nivre, J. and Fang, C.-T. (2017). Universal Dependency evaluation. In Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017), pages 86–95, Gothenburg, Sweden. Association for Computational Linguistics. find
  17. Rodrigues, A. D. (1996). As lı́nguas gerais sul-americanas. Papia, 4(2):6–18. find
  18. Rodrigues, A. D. and Cabral, A. S. A. C. (2011). A contribution to the linguistic history of the lı́ngua geral amazônica. ALFA: Revista de Linguı́stica, 55(2). find
  19. Schuster, S. and Manning, C. D. (2016). Enhanced English Universal Dependencies: An improved representation for natural language understanding tasks. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2371–2378, Portorož, Slovenia. European La… find our card
  20. Simons, G. F., Thomas, A. L. L., and White, C. K. K. (2022). Assessing digital language support on a global scale. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4299–4305, Gyeongju, Republic of Korea. International Committee on Computational Linguistics. find
  21. Straka, M. (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 our card
  22. Straka, M., Hajič, J., and Straková, J. (2016). UDPipe: Trainable pipeline for processing CoNLL-U files performing tokenization, morphological analysis, POS tagging and parsing. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 4290–4297, Po… find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/alencar-2023-yauti-tool-morphosyntactic-analysis-nheengatu/