Aprendizado por Transferência para Correção Automática de Redação

Igor Cataneo  Silveira; Eugénio Ribeiro; Nuno Mamede; Jorge Baptista

doi:10.21814/lm.17.2.493

Transfer Learning for Automatic Essay Scoring

Authors

Igor Cataneo Silveira University of São Paulo https://orcid.org/0000-0003-1599-8347 (unauthenticated)
Eugénio Ribeiro Instituto Universitário de Lisboa https://orcid.org/0000-0001-7147-8675 (unauthenticated)
Nuno Mamede Instituto Superior Técnico, Universidade de Lisboa https://orcid.org/0000-0001-6033-158X (unauthenticated)
Jorge Baptista Faculdade de Ciências Humanas e Sociais, Universidade do Algarve https://orcid.org/0000-0003-4603-4364 (unauthenticated)

DOI:

https://doi.org/10.21814/lm.17.2.493

Keywords:

automatic essay scoring, narrative, Portuguese

Abstract

Automatic Essay Scoring is a field that has been receiving a lot of attention in Portuguese. Among the available datasets, one stands out: a corpus of narrative essays written by students from 5th to 9th grade in Brazil. These essays were evaluated according to four traits: formal register, thematic coherence, narrative rhetorical structure, and textual cohesion. This~work explores the development of a system based on knowledge from another dataset (developed from texts produced for the Brazilian national entrance exam, ENEM) and from other tasks (textual complexity and legibility analysis). This developed system combines neural models, handcrafted features calculated by textual analysis software, and feature selection, through a Two Stage Learning algorithm. With this system, the state-of-the-art performance was enhanced by 9% for the first trait, 5.5% for the third, and 8.9% for the fourth one.

References

Downloads

PDF (Portuguese)

Published

2025-12-31

Issue

Vol. 17 No. 2

Section

Research Articles

License

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

How to Cite

Transfer Learning for Automatic Essay Scoring. (2025). Linguamática, 17(2), 99-116. https://doi.org/10.21814/lm.17.2.493

Download Citation