Update README.md

README.md

@@ -10,7 +10,7 @@ datasets:
 
 # MCTI Text Classification Task (case/uncased) DRAFT
 
-DISCLAIMER: 
+Disclaimer: 
 
 ## According to the abstract,
 
@@ -29,23 +29,16 @@ learning models to improve the comprehension of each sentence. Compared to the b
 the Word2Vec-based approach improved the accuracy rate to 88%. The research results serve as a
 successful case of artificial intelligence in a federal government application.
 
-## Model description
-
 This model focus on a more specific problem, creating a Research Financing Products Portfolio (FPP) outside of
 the Union budget, supported by the Brazilian Ministry of Science, Technology, and Innovation (MCTI). It was 
 introduced in ["Using transfer learning to classify long unstructured texts with small amounts of labeled data"](https://www.scitepress.org/Link.aspx?doi=10.5220/0011527700003318) and first released in
 [this repository](https://huggingface.co/unb-lamfo-nlp-mcti). This model is uncased: it does not make a difference
 between english and English.
 
-Lorem ipsum dolor sit amet, consectetur adipiscing elit. Aliquam sed nibh non enim finibus malesuada. In vitae 
-metus orci. Vestibulum sodales volutpat lorem, eget consectetur nisi viverra vitae. Sed tincidunt accumsan 
-pellentesque. Curabitur urna massa, dapibus sit amet augue quis, aliquam tristique ipsum. In hac habitasse 
-platea dictumst. Fusce aliquet est id mi porttitor tincidunt. Ut imperdiet rutrum eros, ac mollis ipsum 
-auctor ut. Donec lacinia, orci et dignissim molestie, sem ex mollis urna, et blandit nisi leo sit amet mauris. 
 
 Classification_Architecture_model.png
+https://github.com/Marcosdib/S2Query/upload
 
-Nullam pretium condimentum imperdiet.
 
 Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by
 the Hugging Face team.
@@ -71,7 +64,7 @@ bibendum cursus. Nunc volutpat vitae neque ut bibendum.
 
 ## Model variations
 
-BERT has originally been released in base and large variations, for cased and uncased input text. The uncased models 
+XXXX has originally been released in base and large variations, for cased and uncased input text. The uncased models 
 also strips out an accent markers. Chinese and multilingual uncased and cased versions followed shortly after.  
 Modified preprocessing with whole word masking has replaced subpiece masking in a following work, with the release of 
 two models.