Update app.py

app.py

@@ -65,14 +65,16 @@ article = """
 </tr>
 </tbody></table>
 <h3>Conclusion and Future Work</h3>
-If F1 score is considered, the results show that there may be no advantage in using domain-specific masked language models to generate Biomedical QA models. In any case, close results are observed for the biomedical roberta-based models in comparison with the general roberta-based model.
-<ul>
+If F1 score is considered, the results show that there may be no advantage in using domain-specific masked language models to generate Biomedical QA models. 
+In any case, the scores reported for the biomedical roberta-based models are not far below from those of the general roberta-based model.
+
 However, if only unanswerable questions are taken into account, the model with the best F1 score is hackathon-pln-es/roberta-base-biomedical-es-squad2-es.
+
 As future work, the following experiments could be carried out:
 <ul>
-<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.
+<li>Use Biomedical masked-language models that were not trained 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.
 <li>Create a Biomedical training dataset with SQUAD v2 format.
-<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.
+<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.
 <li>Ensamble different models.
 </ul> 
 </p>