lisaterumi commited on
Commit
d005e0e
1 Parent(s): 0d52c12

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -42,7 +42,19 @@ This study was financed in part by the Coordenação de Aperfeiçoamento de Pess
42
 
43
  ## Citation
44
  ```
45
- @article{Schneider_Gumiel_Oliveira_Montenegro_Barzotto_Moro_Pagano_Paraiso_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.} }
 
 
 
 
 
 
 
 
 
 
 
 
46
  ```
47
 
48
  ## Questions?
 
42
 
43
  ## Citation
44
  ```
45
+ @article{Schneider_Gumiel_Oliveira_Montenegro_Barzotto_Moro_Pagano_Paraiso_2023,
46
+ place={Brasil},
47
+ title={Developing a Transformer-based Clinical Part-of-Speech Tagger for Brazilian Portuguese},
48
+ volume={15},
49
+ url={https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/1086},
50
+ DOI={10.59681/2175-4411.v15.iEspecial.2023.1086},
51
+ 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>},
52
+ number={Especial},
53
+ journal={Journal of Health Informatics},
54
+ 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},
55
+ year={2023},
56
+ month={jul.}
57
+ }
58
  ```
59
 
60
  ## Questions?