Update README.md

README.md

@@ -7,7 +7,10 @@ base_model:
 pipeline_tag: text-classification
 widget:
 - text: >-
-    MAEATAE, (Géogr. anc.) anciens peuples de l'île de la grande Bretagne ; ils étoient auprès du mur qui coupoit l'île en deux parties.
+    MAEATAE, (Géogr. anc.) anciens peuples de l'île de la grande Bretagne ; ils
+    étoient auprès du mur qui coupoit l'île en deux parties.
+datasets:
+- GEODE/GeoEDdA-TopoRel
 ---
 
 
@@ -28,9 +31,9 @@ It has been trained on a manually annotated subset of the French *Encyclopédie
 
 <!-- Provide a longer summary of what this model is. -->
 
-- **Developed by:** [Ludovic Moncla](https://ludovicmoncla.github.io) in the framework of the [GEODE](https://geode-project.github.io) project.
+- **Authors:** Bin Yang, [Ludovic Moncla](https://ludovicmoncla.github.io), [Fabien Duchateau](https://perso.liris.cnrs.fr/fabien.duchateau/) and [Frédérique Laforest](https://perso.liris.cnrs.fr/flaforest/) in the framework of the [ECoDA](https://liris.cnrs.fr/projet-institutionnel/fil-2025-projet-ecoda) and [GEODE](https://geode-project.github.io) projects
 - **Model type:** Text classification
-- **Repository:** [https://github.com/GEODE-project/semantic-entity-detection-encyclopedia](https://github.com/GEODE-project/semantic-entity-detection-encyclopedia)
+- **Repository:** [https://gitlab.liris.cnrs.fr/ecoda/encyclopedia2geokg](https://gitlab.liris.cnrs.fr/ecoda/encyclopedia2geokg)
 - **Language(s) (NLP):** French
 - **License:** cc-by-nc-4.0
 
@@ -41,20 +44,20 @@ It has been trained on a manually annotated subset of the French *Encyclopédie
 The tagset is as follows:
 - **Place**: encyclopedia entry describing the name of a place (such as a city, a river, a country, etc.)
 - **Person**: encyclopedia entry describing the name of a people or community
-- **Misc**: encyclopedia entry describing any other type of entity (such as abstract geographic concepts, cross-references to other entries, etc.)
+- **Other**: encyclopedia entry describing any other type of entity (such as abstract geographic concepts, cross-references to other entries, etc.)
 
 
 ## Dataset
 
 
-The model was trained using a set of 1423 entries (only first paragraphs) classified as 'Geography' (using this model: https://huggingface.co/GEODE/bert-base-multilingual-cased-edda-domain-classification). First paragraphs 
-The datasets have the following distribution of entries among datasets and classes: 
+The model was trained using the [GeoEDdA-TopoRel](https://huggingface.co/datasets/GEODE/GeoEDdA-TopoRel) dataset.
+The dataset is splitted into train, validation and test sets which have the following distribution of entries among classes: 
 
 |   | Train | Validation | Test|
 |---|:---:|:---:|:---:|
-| Place | 707 | 125 | 147|
-| Person | 123 | 22 | 26 |
-| Misc | 197 | 35 | 41 |
+| Place | 1,800 | 225 | 225|
+| Person | 200 | 25 | 25 |
+| Misc | 200 | 25 | 25 |
 
 
 ## Evaluation
@@ -65,7 +68,7 @@ The datasets have the following distribution of entries among datasets and class
 
 |   | Precision | Recall | F-score |
 |---|:---:|:---:|:---:|
-|    | 0.95   | 0.95   | 0.95 | 
+|    | 0.980   | 0.978   | 0.979 | 
 
 
 
@@ -73,9 +76,9 @@ The datasets have the following distribution of entries among datasets and class
 
 |   | Precision | Recall | F-score | Support |
 |---|:---:|:---:|:---:|:---:|
-| Place    |  0.97  |  0.97  |  0.97 | 147 |
-| Person   |  0.92  |  0.92  |  0.92 | 26 |
-| Misc     |  0.90  |  0.90  |  0.90 | 41 |
+| Place    |  0.99  |  0.98  |  0.99 | 225 |
+| Person   |  1.00  |  0.96  |  0.98 | 25 |
+| Other     |  0.83  |  0.96  |  0.89 | 25 |
 
 
 
@@ -106,9 +109,9 @@ for sample in samples:
     print(pipe(sample))
 
 # Output
-[{'label': 'Place', 'score': 0.9956912398338318}]
-[{'label': 'Person', 'score': 0.9895496368408203}]
-[{'label': 'Misc', 'score': 0.993893563747406}]
+[{'label': 'Place', 'score': 0.9984742999076843}]
+[{'label': 'Person', 'score': 0.9927592277526855}]
+[{'label': 'Other', 'score': 0.9885557293891907}]
 
 ```
 
@@ -124,4 +127,4 @@ This model was trained entirely on French encyclopaedic entries classified as Ge
 ## Acknowledgement
 
 The authors are grateful to the [ASLAN project](https://aslan.universite-lyon.fr) (ANR-10-LABX-0081) of the Université de Lyon, for its financial support within the French program "Investments for the Future" operated by the National Research Agency (ANR).
-Data courtesy the [ARTFL Encyclopédie Project](https://artfl-project.uchicago.edu), University of Chicago.
+Data courtesy the [ARTFL Encyclopédie Project](https://artfl-project.uchicago.edu), University of Chicago.