Update app.py
Browse files
app.py
CHANGED
|
@@ -77,7 +77,7 @@ As future work, the following experiments could be carried out:
|
|
| 77 |
|
| 78 |
<ul>
|
| 79 |
<li>Use Biomedical masked-language models that were not generated from scratch from a Biomedical corpus but have been adapted from a general model, so as not to lose words and features of Spanish that are also present in Biomedical questions and articles.
|
| 80 |
-
<li>Create a Biomedical training dataset with SQUAD v2 format
|
| 81 |
<li>Generate a new and bigger validation dataset based on questions and contexts generated directly in Spanish and not translated as in SQUAD_Es v2.
|
| 82 |
<li>Ensamble different models.
|
| 83 |
</ul>
|
|
|
|
| 77 |
|
| 78 |
<ul>
|
| 79 |
<li>Use Biomedical masked-language models that were not generated from scratch from a Biomedical corpus but have been adapted from a general model, so as not to lose words and features of Spanish that are also present in Biomedical questions and articles.
|
| 80 |
+
<li>Create a Biomedical training dataset with SQUAD v2 format.
|
| 81 |
<li>Generate a new and bigger validation dataset based on questions and contexts generated directly in Spanish and not translated as in SQUAD_Es v2.
|
| 82 |
<li>Ensamble different models.
|
| 83 |
</ul>
|