Hugging Face's logo

GEODE
/
bert-base-multilingual-cased-place-entry-classification

Text Classification
Safetensors
French
bert
Model card Files
xet
Community
lmoncla commited on
Commit
c8fb056
·
verified ·
1 Parent(s): 0056372

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -12
README.md CHANGED
@@ -39,26 +39,37 @@ It has been trained on a manually annotated subset of the French *Encyclopédie
39
 
40
 
41
  The tagset is as follows:
42
- TODO
 
 
 
 
 
 
 
 
 
 
43
 
44
  ## Dataset
45
 
46
 
47
- 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
48
  The datasets have the following distribution of entries among datasets and classes:
49
 
50
  | | Train | Validation | Test|
51
  |---|:---:|:---:|:---:|
52
- | Ville | 4431 | 782 | 921 |
53
- | Île | 603 | 107 | 125 |
54
- | Région | 444 | 79 | 93 |
55
- | Rivière | 356 | 63 | 74 |
56
- | Montagne | 149 | 26 | 31 |
57
- | Pays | 74 | 13 | 15 |
58
- | Mer | 64 | 11 | 13 |
59
- | Autre | 52 | 9 | 11 |
60
- | ConstructionHumaine | 49 | 9 | 10 |
61
- | Lac | 41 | 7 | 8 |
 
62
 
63
 
64
  ## Evaluation
 
39
 
40
 
41
  The tagset is as follows:
42
+ - **Ville**: villes, bourgs, villages, etc.
43
+ - **Île**: îles, presqu'îles, etc.
44
+ - **Région**: régions, contrées, provinces, cercles, etc.
45
+ - **Rivière**: rivières, fleuves,etc.
46
+ - **Montagne**: montagnes, vallées, etc.
47
+ - **Pays**: pays, royaumes, etc.
48
+ - **Mer**: mer, golphe, baie, etc.
49
+ - **Autre**: promontoires, caps, rivages, déserts, etc.
50
+ - **ConstructionHumaine**: ports, châteaux, forteresses, abbayes, etc.
51
+ - **Lac**: lacs, étangs, marais, etc.
52
+
53
 
54
  ## Dataset
55
 
56
 
57
+ The model was trained using a set of 1423 entries classified as 'Geography' (using this model: https://huggingface.co/GEODE/bert-base-multilingual-cased-edda-domain-classification). First paragraphs
58
  The datasets have the following distribution of entries among datasets and classes:
59
 
60
  | | Train | Validation | Test|
61
  |---|:---:|:---:|:---:|
62
+ | Ville | 4294 | 920 | 921 |
63
+ | Île | 590 | 127 | 126 |
64
+ | Région | 432 | 92 | 93 |
65
+ | Rivière | 352 | 75 | 75 |
66
+ | Montagne | 146 | 31 | 31 |
67
+ | Pays | 72 | 15 | 16 |
68
+ | Mer | 62 | 14 | 13 |
69
+ | ConstructionHumaine | 49 | 11 | 10 |
70
+ | Lac | 41 | 9 | 9 |
71
+ | Autre | 27 | 6 | 6 |
72
+
73
 
74
 
75
  ## Evaluation