lisaterumi/postagger-portuguese

POS-Tagger Portuguese

We fine-tuned the BERTimbau model with the MacMorpho corpus for the Post-Tagger task, with 10 epochs, achieving a general F1-Score of 0.9826.

Metrics:

              Precision  Recall  F1    Suport
accuracy                         0.98  33729
macro avg     0.96       0.95    0.95  33729
weighted avg  0.98       0.98    0.98  33729

F1:  0.9826 Accuracy:  0.9826

Parameters:

nclasses = 27
nepochs = 30
batch_size = 32
batch_status = 32
learning_rate = 1e-5
early_stop = 3
max_length = 200

Tags:

Tag	Meaning
ADJ	Adjetivo
ADV	Advérbio
ADV-KS	Advérbio conjuntivo subordinado
ADV-KS-REL	Advérbio relativo subordinado
ART	Artigo
CUR	Moeda
IN	Interjeição
KC	Conjunção coordenativa
KS	Conjunção subordinativa
N	Substantivo
NPROP	Substantivo próprio
NUM	Número
PCP	Particípio
PDEN	Palavra denotativa
PREP	Preposição
PROADJ	Pronome Adjetivo
PRO-KS	Pronome conjuntivo subordinado
PRO-KS-REL	Pronome relativo conectivo subordinado
PROPESS	Pronome pessoal
PROSUB	Pronome nominal
V	Verbo
VAUX	Verbo auxiliar

How to cite

@article{
Schneider_postagger_2023,
place={Brasil},
title={Developing a Transformer-based Clinical Part-of-Speech Tagger for Brazilian Portuguese},
volume={15},
url={https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/1086},
DOI={10.59681/2175-4411.v15.iEspecial.2023.1086},
abstractNote={<p>Electronic Health Records are a valuable source of information to be extracted by means of natural language processing (NLP) tasks, such as morphosyntactic word tagging. Although there have been significant advances in health NLP, such as the Transformer architecture, languages such as Portuguese are still underrepresented. This paper presents taggers developed for Portuguese texts, fine-tuned using BioBERtpt (clinical/biomedical) and BERTimbau (generic) models on a POS-tagged corpus. We achieved an accuracy of 0.9826, state-of-the-art for the corpus used. In addition, we performed a human-based evaluation of the trained models and others in the literature, using authentic clinical narratives. Our clinical model achieved 0.8145 in accuracy compared to 0.7656 for the generic model. It also showed competitive results compared to models trained specifically with clinical texts, evidencing domain impact on the base model in NLP tasks.</p>},
number={Especial}, journal={Journal of Health Informatics},
author={Schneider, Elisa Terumi Rubel and Gumiel, Yohan Bonescki and Oliveira, Lucas Ferro Antunes de and Montenegro, Carolina de Oliveira and Barzotto, Laura Rubel and Moro, Claudia and Pagano, Adriana and Paraiso, Emerson Cabrera},
year={2023},
month={jul.} }

Questions?

Please, post a Github issue on the NLP Portuguese POS-Tagger.