Update README.md

README.md

@@ -15,9 +15,6 @@ language:
 - fr
 widget:
 - text: "Assurés de disputer l'Euro 2024 en Allemagne l'été prochain (du 14 juin au 14 juillet) depuis leur victoire aux Pays-Bas, les Bleus ont fait le nécessaire pour avoir des certitudes. Avec six victoires en six matchs officiels et un seul but encaissé, Didier Deschamps a consolidé les acquis de la dernière Coupe du monde. Les joueurs clés sont connus : Kylian Mbappé, Aurélien Tchouameni, Antoine Griezmann, Ibrahima Konaté ou encore Mike Maignan."
-inference:
-  parameters:
-    aggregation_strategy: "max"
 library_name: transformers
 pipeline_tag: token-classification
 co2_eq_emissions: 20
@@ -108,40 +105,30 @@ The evaluation was carried out using the [**evaluate**](https://pypi.org/project
     <tr>
         <td rowspan="3"><br>Camembert-base-frenchNER_4entities</td>
         <td><br>Precision</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.973</td>
+        <td><br>0.951</td>
+        <td><br>0.8877</td>
+        <td><br>0.850</td>
+        <td><br>0.993</td>
+        <td><br>0.984</td>
     </tr>
     <tr>
         <td><br>Recall</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.983</td>
+        <td><br>0.964</td>
+        <td><br>0.918</td>
+        <td><br>0.781</td>
+        <td><br>0.993</td>
+        <td><br>0.984</td>
     </tr>
     <tr>
         <td>F1</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
-    </tr>
-    <tr>
-        <td></td>
-        <td><br>Number</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.978</td>
+        <td><br>0.958</td>
+        <td><br>0.903</td>
+        <td><br>0.814</td>
+        <td><br>0.993</td>
+        <td><br>0.984</td>
     </tr>
 </tbody>
 </table>
@@ -168,40 +155,30 @@ In detail:
     <tr>
         <td rowspan="3"><br>Camembert-base-frenchNER_4entities</td>
         <td><br>Precision</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.954</td>
+        <td><br>0.893</td>
+        <td><br>0.851/td>
+        <td><br>0.849</td>
+        <td><br>0.979</td>
+        <td><br>0.954</td>
     </tr>
     <tr>
         <td><br>Recall</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.967</td>
+        <td><br>0.887/td>
+        <td><br>0.883</td>
+        <td><br>0.855</td>
+        <td><br>0.974</td>
+        <td><br>0.954</td>
     </tr>
     <tr>
         <td>F1</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
-    </tr>
-    <tr>
-        <td></td>
-        <td><br>Number</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.960</td>
+        <td><br>0.890</td>
+        <td><br>0.867</td>
+        <td><br>0.852</td>
+        <td><br>0.977</td>
+        <td><br>0.954</td>
     </tr>
 </tbody>
 </table>
@@ -225,40 +202,30 @@ In detail:
     <tr>
         <td rowspan="3"><br>Camembert-base-frenchNER_4entities</td>
         <td><br>Precision</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.976</td>
+        <td><br>0.961</td>
+        <td><br>0.91</td>
+        <td><br>0.829</td>
+        <td><br>0.991</td>
+        <td><br>0.983</td>
     </tr>
     <tr>
         <td><br>Recall</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.993</td>
+        <td><br>0.985</td>
+        <td><br>0.967</td>
+        <td><br>0.993</td>
+        <td><br>0.719</td>
+        <td><br>0.983</td>
     </tr>
     <tr>
         <td>F1</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
-    </tr>
-    <tr>
-        <td></td>
-        <td><br>Number</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.985</td>
+        <td><br>0.973</td>
+        <td><br>0.938</td>
+        <td><br>0.770</td>
+        <td><br>0.992</td>
+        <td><br>0.983</td>
     </tr>
 </tbody>
 </table>
@@ -283,40 +250,30 @@ In detail:
     <tr>
         <td rowspan="3"><br>Camembert-base-frenchNER_4entities</td>
         <td><br>Precision</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.970</td>
+        <td><br>0.944</td>
+        <td><br>0.872</td>
+        <td><br>0.878</td>
+        <td><br>0.996</td>
+        <td><br>0.986</td>
     </tr>
     <tr>
         <td><br>Recall</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.969</td>
+        <td><br>0.947</td>
+        <td><br>0.880</td>
+        <td><br>0.866</td>
+        <td><br>0.996</td>
+        <td><br>0.986</td>
     </tr>
     <tr>
         <td>F1</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
-    </tr>
-    <tr>
-        <td></td>
-        <td><br>Number</td>
-        <td><br>A</td>
-        <td><br>B</td>
-        <td><br>C</td>
-        <td><br>D</td>
-        <td><br>E</td>
-        <td><br>F</td>
+        <td><br>0.970</td>
+        <td><br>0.945</td>
+        <td><br>0.876</td>
+        <td><br>0.872</td>
+        <td><br>0.996</td>
+        <td><br>0.986</td>
     </tr>
 </tbody>
 </table>
@@ -328,16 +285,89 @@ In detail:
 ```python
 from transformers import pipeline
 
-ner = pipeline('question-answering', model='CATIE-AQ/Camembert-base-frenchNER_4entities', tokenizer='CATIE-AQ/Camembert-base-frenchNER_4entities', grouped_entities=True)
+ner = pipeline('question-answering', model='CATIE-AQ/Camembert-base-frenchNER_4entities', tokenizer='CATIE-AQ/Camembert-base-frenchNER_4entities', aggregation_strategy="simple")
 
-result = ner(
+results = ner(
 "Assurés de disputer l'Euro 2024 en Allemagne l'été prochain (du 14 juin au 14 juillet) depuis leur victoire aux Pays-Bas, les Bleus ont fait le nécessaire pour avoir des certitudes. Avec six victoires en six matchs officiels et un seul but encaissé, Didier Deschamps a consolidé les acquis de la dernière Coupe du monde. Les joueurs clés sont connus : Kylian Mbappé, Aurélien Tchouameni, Antoine Griezmann, Ibrahima Konaté ou encore Mike Maignan."
 )
 
+
+# Note : the aggregation_strategy parameter does not return the results as expected, so we need to do some post-processing
+dict_to_del = []
+for idx in range(len(results)-1):
+    if results[idx]["end"] == results[idx+1]["start"]:
+        results[idx+1]["word"] = results[idx]["word"]+results[idx+1]["word"]
+        results[idx+1]["score"] = (results[idx]["score"]+results[idx+1]["score"])/2
+        results[idx+1]["start"] = results[idx]["start"]
+        dict_to_del.append(idx)
+results = [j for i, j in enumerate(results) if i not in dict_to_del]
+
+dict_to_del = []
+for i in range(len(to_print)-1):
+    if (to_print[i]["end"] == to_print[i+1]["start"]-1):
+        to_print[i+1]["word"] = to_print[i]["word"]+" "+to_print[i+1]["word"]
+        to_print[i+1]["score"] = (to_print[i]["score"]+to_print[i+1]["score"])/2
+        to_print[i+1]["start"] = to_print[i]["start"]
+        dict_to_del.append(i)
+to_print = [j for i, j in enumerate(to_print) if i not in dict_to_del]
+
 print(result)
-```
 ```python
-
+[{'entity_group': 'MISC',
+  'score': 0.9404951632022858,
+  'word': 'Euro 2024',
+  'start': 22,
+  'end': 31},
+ {'entity_group': 'LOC',
+  'score': 0.96980727,
+  'word': 'Allemagne',
+  'start': 35,
+  'end': 44},
+ {'entity_group': 'LOC',
+  'score': 0.8612850904464722,
+  'word': 'Pays-Bas',
+  'start': 112,
+  'end': 120},
+ {'entity_group': 'ORG',
+  'score': 0.8148028254508972,
+  'word': 'les Bleus',
+  'start': 122,
+  'end': 131},
+ {'entity_group': 'PER',
+  'score': 0.9994482398033142,
+  'word': 'Didier Deschamps',
+  'start': 250,
+  'end': 266},
+ {'entity_group': 'MISC',
+  'score': 0.84807388484478,
+  'word': 'dernière Coupe du monde',
+  'start': 296,
+  'end': 319},
+ {'entity_group': 'PER',
+  'score': 0.9996860176324844,
+  'word': 'Kylian Mbappé',
+  'start': 352,
+  'end': 365},
+ {'entity_group': 'PER',
+  'score': 0.9996881932020187,
+  'word': 'Aurélien Tchouameni',
+  'start': 367,
+  'end': 386},
+ {'entity_group': 'PER',
+  'score': 0.9996924996376038,
+  'word': 'Antoine Griezmann',
+  'start': 388,
+  'end': 405},
+ {'entity_group': 'PER',
+  'score': 0.9996860027313232,
+  'word': 'Ibrahima Konaté',
+  'start': 407,
+  'end': 422},
+ {'entity_group': 'PER',
+  'score': 0.9996623992919922,
+  'word': 'Mike Maignan',
+  'start': 433,
+  'end': 445}]
 ```
 
 ### Try it through Space