Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Ribeiro, E., Antunes, D., Mamede, N. & Baptista, J. (2025). Exploring few-shot approaches to automatic text complexity assessment in European Portuguese. Journal of the Brazilian Computer Society. 31 (1), 690-710
Exportar Referência (IEEE) 
E. A. Ribeiro et al.,  "Exploring few-shot approaches to automatic text complexity assessment in European Portuguese", in Journal of the Brazilian Computer Society, vol. 31, no. 1, pp. 690-710, 2025
Exportar BibTeX 
@article{ribeiro2025_1766315990615,
	author = "Ribeiro, E. and Antunes, D. and Mamede, N. and Baptista, J.",
	title = "Exploring few-shot approaches to automatic text complexity assessment in European Portuguese",
	journal = "Journal of the Brazilian Computer Society",
	year = "2025",
	volume = "31",
	number = "1",
	doi = "10.5753/jbcs.2025.5820",
	pages = "690-710",
	url = "https://journals-sol.sbc.org.br/index.php/jbcs/about"
}
Exportar RIS 
TY  - JOUR
TI  - Exploring few-shot approaches to automatic text complexity assessment in European Portuguese
T2  - Journal of the Brazilian Computer Society
VL  - 31
IS  - 1
AU  - Ribeiro, E.
AU  - Antunes, D.
AU  - Mamede, N.
AU  - Baptista, J.
PY  - 2025
SP  - 690-710
SN  - 0104-6500
DO  - 10.5753/jbcs.2025.5820
UR  - https://journals-sol.sbc.org.br/index.php/jbcs/about
AB  - The automatic assessment of text complexity has an important role to play in the context of language education. In this study, we shift the focus from L2 learners to adult native speakers with low literacy by exploring the new iRead4Skills dataset in European Portuguese. Furthermore, instead of relying on classical machine learning approaches or fine-tuning a pre-trained language model, we leverage the capabilities of prompt-based Large Language Models (LLMs), with a special focus on few-shot prompting approaches. We explore prompts with varying degrees of information, as well as different example selection approaches. Overall, the results of our experiments reveal that even a single example significantly increases the performance of the model and that few-shot approaches generalize better than fine-tuned models. However, automatic complexity assessment is a difficult and highly subjective task that is still far from solved.
ER  -