Update README.md

README.md

@@ -15,7 +15,7 @@ This is a reduced version of the Portuguese capitalisation and punctuation resto
 
 You can try the model in the following [SPACE](https://huggingface.co/spaces/VOCALINLP/punctuation_and_capitalization_restoration_sanivert)
 ## Details of the dataset
-
+The model was fine-tuned for punctuation restoration using clinical reports and the OpusParaCrawl dataset.
 
 ## Evaluation Metrics 
 
@@ -23,6 +23,9 @@ You can try the model in the following [SPACE](https://huggingface.co/spaces/VOC
 This work was funded by the Spanish Government, the Spanish Ministry of Economy and Digital Transformation through the Digital Transformation through the "Recovery, Transformation and Resilience Plan" and also funded by the European Union NextGenerationEU/PRTR through the research project 2021/C005/0015007
 
 ## How to use the model
+The metrics used to the evaluation of the model are the Macro and the Weighted F1 scores.
+
+
 
 ```py
 from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
@@ -30,31 +33,38 @@ import torch
 
 def get_result_text_es_pt (list_entity, text, lang):
     result_words = []
+    tmp_word = ""
     if lang == "es":
         punc_tags = ['¿', '?', '¡', '!', ',', '.', ':']
     else:
         punc_tags = ['?', '!', ',', '.', ':']
-
-    for entity in list_entity:
+    
+    for idx, entity in enumerate(list_entity): 
         tag = entity["entity"]
         word = entity["word"]
         start = entity["start"]
         end = entity["end"]
-
+        
         # check punctuation
         punc_in = next((p for p in punc_tags if p in tag), "")
-
+                
         subword = False
         # check subwords
-        if word[0] == "#":
+        if word[0] == "#": 
             subword = True
-            if punc_in != "":
-                word = result_words[-1].replace(punc_in, "") + text[start:end]
-            else:
-                word = result_words[-1] + text[start:end]
-
-        if tag == "l":
-            word = word
+            if tmp_word == "":
+                p_s = list_entity[idx-1]["start"]
+                p_e = list_entity[idx-1]["end"]
+                tmp_word = text[p_s:p_e] + text[start:end]
+            else: 
+                tmp_word = tmp_word + text[start:end]
+            word = tmp_word
+        else:
+            tmp_word = ""
+            word = text[start:end]
+            
+        if tag == "l": 
+            word = word 
         elif tag == "u":
             word = word.capitalize()
         # case with punctuation
@@ -62,9 +72,12 @@ def get_result_text_es_pt (list_entity, text, lang):
             if tag[-1] == "l":
                 word = (punc_in + word) if punc_in in ["¿", "¡"] else (word + punc_in)
             elif tag[-1] == "u":
-                word = (punc_in + word.capitalize()) if punc_in in ["¿", "¡"] else (word.capitalize() + punc_in)
-
-        if subword == True:
+                word = (punc_in + word.capitalize()) if punc_in in ["¿", "¡"] else (word.capitalize() + punc_in)     
+        
+        if tag != "l":
+            word = '<span style="font-weight:bold; color:rgb(142, 208, 129);">' + word + '</span>'
+		
+        if subword == True: 
             result_words[-1] = word
         else:
             result_words.append(word)