Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 153.81 KB
Add to list
  1. Search results
  2. Comparing LLM prompting with Cross-li...

Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages

David Ifeoluwa Adelani, A. Seza Doğruöz (UGent) , Andre Coneglian and Atul Ojha
(2024) Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024). p.34-41
Author
Organization
Abstract
Large Language Models are transforming NLP for a lot of tasks. However, how LLMs perform NLP tasks for LRLs is less explored. In alliance with the theme track of the NAACL’24, we focus on 12 low-resource languages (LRLs) from Brazil, 2 LRLs from Africa and 2 high-resource languages (HRLs) (e.g., English and Brazilian Portuguese). Our results indicate that the LLMs perform worse for the labeling of LRLs in comparison to HRLs in general. We explain the reasons behind this failure and provide an error analyses through examples from 2 Brazilian LRLs.
Keywords
Brazilian Languages, Multilingual, Large Language Models, Low Resource Languages

Downloads

  • Download
    Dogruoz NAACL24.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 153.81 KB

Citation

Please use this url to cite or link to this publication:

MLA
Adelani, David Ifeoluwa, et al. “Comparing LLM Prompting with Cross-Lingual Transfer Performance on Indigenous and Low-Resource Brazilian Languages.” Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), edited by Manuel Mager et al., Association for Computational Linguistics (ACL), 2024, pp. 34–41, doi:10.18653/v1/2024.americasnlp-1.5.
APA
Adelani, D. I., Doğruöz, A. S., Coneglian, A., & Ojha, A. (2024). Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages. In M. Mager, A. Ebrahimi, S. Rijhwani, A. Oncevay, L. Chiruzzo, R. Pugh, & K. von der Wense (Eds.), Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024) (pp. 34–41). https://doi.org/10.18653/v1/2024.americasnlp-1.5
Chicago author-date
Adelani, David Ifeoluwa, A. Seza Doğruöz, Andre Coneglian, and Atul Ojha. 2024. “Comparing LLM Prompting with Cross-Lingual Transfer Performance on Indigenous and Low-Resource Brazilian Languages.” In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), edited by Manuel Mager, Abteen Ebrahimi, Shruti Rijhwani, Arturo Oncevay, Luis Chiruzzo, Robert Pugh, and Katharina von der Wense, 34–41. Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2024.americasnlp-1.5.
Chicago author-date (all authors)
Adelani, David Ifeoluwa, A. Seza Doğruöz, Andre Coneglian, and Atul Ojha. 2024. “Comparing LLM Prompting with Cross-Lingual Transfer Performance on Indigenous and Low-Resource Brazilian Languages.” In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), ed by. Manuel Mager, Abteen Ebrahimi, Shruti Rijhwani, Arturo Oncevay, Luis Chiruzzo, Robert Pugh, and Katharina von der Wense, 34–41. Association for Computational Linguistics (ACL). doi:10.18653/v1/2024.americasnlp-1.5.
Vancouver
1.
Adelani DI, Doğruöz AS, Coneglian A, Ojha A. Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages. In: Mager M, Ebrahimi A, Rijhwani S, Oncevay A, Chiruzzo L, Pugh R, et al., editors. Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024). Association for Computational Linguistics (ACL); 2024. p. 34–41.
IEEE
[1]
D. I. Adelani, A. S. Doğruöz, A. Coneglian, and A. Ojha, “Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages,” in Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), Mexico City, New Mexico, 2024, pp. 34–41.
@inproceedings{01JNNJA73PK76K3A8204XAVYB0,
  abstract     = {{Large Language Models are transforming NLP for a lot of tasks. However, how LLMs perform NLP tasks for LRLs is less explored. In alliance with the theme track of the NAACL’24, we focus on 12 low-resource languages (LRLs) from Brazil, 2 LRLs from Africa and 2 high-resource languages (HRLs) (e.g., English and Brazilian Portuguese). Our results indicate that the LLMs perform worse for the labeling of LRLs in comparison to HRLs in general. We explain the reasons behind this failure and provide an error analyses through examples from 2 Brazilian LRLs.}},
  author       = {{Adelani, David Ifeoluwa and Doğruöz, A. Seza and Coneglian, Andre and Ojha, Atul}},
  booktitle    = {{Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)}},
  editor       = {{Mager, Manuel and Ebrahimi, Abteen and Rijhwani, Shruti and Oncevay, Arturo and Chiruzzo, Luis and Pugh, Robert and von der Wense, Katharina}},
  isbn         = {{9798891761087}},
  keywords     = {{Brazilian Languages,Multilingual,Large Language Models,Low Resource Languages}},
  language     = {{eng}},
  location     = {{Mexico City, New Mexico}},
  pages        = {{34--41}},
  publisher    = {{Association for Computational Linguistics (ACL)}},
  title        = {{Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages}},
  url          = {{http://doi.org/10.18653/v1/2024.americasnlp-1.5}},
  year         = {{2024}},
}
Altmetric
View in Altmetric