Enhancing Named Entity Recognition in Portuguese Literary Texts with Adaptive Models
Abstract
We investigate pre-training strategies to enhance Named Entity Recognition (NER) in Portuguese literary texts. We introduce two domain-adaptive models, LitBERT-CRF and LitBERTimbau, built on general-domain language models. We also evaluate transfer learning across domains alongside a general-domain baseline (BERT-CRF). Overall, our findings highlight the efficiency of our strategies and their implications for literary NER tasks. Furthermore, experimental results reveal the adapted and domain-specific models outperform the generic baseline with an F1 score of over 75% in a strict evaluation scenario and over 80\% in a partial scenario.
Copyright (c) 2025 Mariana O. Silva, Mirella Moro
This work is licensed under a Creative Commons Attribution 4.0 International 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).
