lmoncla commited on
Commit
e544a54
·
verified ·
1 Parent(s): ce7854e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -7,7 +7,7 @@ base_model:
7
  pipeline_tag: text-classification
8
  widget:
9
  - text: >-
10
- MAEATAE, (Géogr. anc.) anciens peuples de l'île de la grande Bretagne ; ils étoient auprès du mur qui coupoit l'île en deux parties.
11
  ---
12
 
13
 
@@ -39,18 +39,19 @@ It has been trained on a manually annotated subset of the French *Encyclopédie
39
 
40
 
41
  The tagset is as follows:
42
- - **single**:
43
- - **multiple**:
44
 
45
  ## Dataset
46
 
47
 
48
- The model was trained using a set of 8665 entries classified as 'Place' (using this model: https://huggingface.co/GEODE/bert-base-multilingual-cased-geography-entry-classification) among entries classified as 'Geography' (using this model: https://huggingface.co/GEODE/bert-base-multilingual-cased-edda-domain-classification).
49
  The datasets have the following distribution of entries among datasets and classes:
50
 
51
  | | Train | Validation | Test|
52
  |---|:---:|:---:|:---:|
53
-
 
54
 
55
 
56
  ## Evaluation
@@ -58,25 +59,24 @@ The datasets have the following distribution of entries among datasets and class
58
 
59
  * Overall macro-average model performances
60
 
61
- | Precision | Recall | F-score |
62
  |:---:|:---:|:---:|
63
-
64
 
65
 
66
  * Overall weighted-average model performances
67
 
68
  | Precision | Recall | F-score |
69
  |:---:|:---:|:---:|
70
-
71
 
72
 
73
  * Model performances (Test set)
74
 
75
  | | Precision | Recall | F-score | Support |
76
  |---|:---:|:---:|:---:|:---:|
77
-
78
-
79
-
80
 
81
 
82
 
@@ -98,7 +98,7 @@ pipe = pipeline("text-classification", model=model, tokenizer=tokenizer, truncat
98
 
99
  samples = [
100
  "* ALBI, (Géog.) ville de France, capitale de l'Albigeois, dans le haut Languedoc : elle est sur le Tarn. Long. 19. 49. lat. 43. 55. 44.",
101
- "* ARCALU (Principauté d') petit état des Tartares-Monguls, sur la riviere d'Hoamko, commence la grande muraille de la Chine, sous le 122e degré de longitude & le 42e de latitude septentrionale."
102
  ]
103
 
104
 
 
7
  pipeline_tag: text-classification
8
  widget:
9
  - text: >-
10
+ PEGOE, (Géog. anc.) 1°. ville de l'Achaie, dans la Mégaride ; 2°. ville de l'Hellespont, selon Ortelius ; 3°. ville de l'île de Cypre ou de la Cyrénie, selon Etienne le géographe.
11
  ---
12
 
13
 
 
39
 
40
 
41
  The tagset is as follows:
42
+ - **single**: only one place is described
43
+ - **multiple**: several places are described (a single name with multiple locations)
44
 
45
  ## Dataset
46
 
47
 
48
+ The model was trained using a set of 8658 entries classified as 'Place' (using this model: https://huggingface.co/GEODE/bert-base-multilingual-cased-geography-entry-classification) among entries classified as 'Geography' (using this model: https://huggingface.co/GEODE/bert-base-multilingual-cased-edda-domain-classification).
49
  The datasets have the following distribution of entries among datasets and classes:
50
 
51
  | | Train | Validation | Test|
52
  |---|:---:|:---:|:---:|
53
+ | Single | 5760 | 1235 | 1234 |
54
+ | Multiple | 300 | 64 | 65 |
55
 
56
 
57
  ## Evaluation
 
59
 
60
  * Overall macro-average model performances
61
 
62
+ | Precision | Recall | F-score |
63
  |:---:|:---:|:---:|
64
+ | 0.92 | 0.92 | 0.92 |
65
 
66
 
67
  * Overall weighted-average model performances
68
 
69
  | Precision | Recall | F-score |
70
  |:---:|:---:|:---:|
71
+ | 0.98 | 0.98 | 0.98 |
72
 
73
 
74
  * Model performances (Test set)
75
 
76
  | | Precision | Recall | F-score | Support |
77
  |---|:---:|:---:|:---:|:---:|
78
+ | Multiple | 0.85 | 0.85 | 0.85 | 65 |
79
+ | Single | 0.99 | 0.99 | 0.99 | 1234 |
 
80
 
81
 
82
 
 
98
 
99
  samples = [
100
  "* ALBI, (Géog.) ville de France, capitale de l'Albigeois, dans le haut Languedoc : elle est sur le Tarn. Long. 19. 49. lat. 43. 55. 44.",
101
+ "PEGOE, (Géog. anc.) 1°. ville de l'Achaie, dans la Mégaride ; 2°. ville de l'Hellespont, selon Ortelius ; 3°. ville de l'île de Cypre ou de la Cyrénie, selon Etienne le géographe. "
102
  ]
103
 
104