loic-dagnas-sinequa commited on
Commit
da17af4
·
1 Parent(s): 8561a46

Update README.md

Browse files



@basilevc


@skirres


I have specified that by Chinese we meant simplified chinese as requested by Ariane here.

I have also reorder the language by the alphabetical order of the language codes

Just note that zs is not recognized by huggingface language tags.

Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -8,7 +8,7 @@ language:
8
  - ja
9
  - nl
10
  - pt
11
- - zh
12
  ---
13
 
14
  # Model Card for `passage-ranker.strawberry`
@@ -22,15 +22,15 @@ Model name: `passage-ranker.strawberry`
22
 
23
  The model was trained and tested in the following languages:
24
 
25
- - Chinese
26
- - Dutch
27
  - English
 
28
  - French
29
- - German
30
  - Italian
31
  - Japanese
 
32
  - Portuguese
33
- - Spanish
34
 
35
  Besides the aforementioned languages, basic support can be expected for additional 91 languages that were used during
36
  the pretraining of the base model (see Appendix A of [XLM-R paper](https://arxiv.org/abs/1911.02116)).
@@ -111,10 +111,10 @@ We evaluated the model on the datasets of the [MIRACL benchmark](https://github.
111
  multilingual capacities. Note that not all training languages are part of the benchmark, so we only report the metrics
112
  for the existing languages.
113
 
114
- | Language | NDCG@10 |
115
- |:---------|--------:|
116
- | Chinese | 0.414 |
117
- | French | 0.382 |
118
- | German | 0.320 |
119
- | Japanese | 0.479 |
120
- | Spanish | 0.418 |
 
8
  - ja
9
  - nl
10
  - pt
11
+ - zs
12
  ---
13
 
14
  # Model Card for `passage-ranker.strawberry`
 
22
 
23
  The model was trained and tested in the following languages:
24
 
25
+ - German
 
26
  - English
27
+ - Spanish
28
  - French
 
29
  - Italian
30
  - Japanese
31
+ - Dutch
32
  - Portuguese
33
+ - Chinese
34
 
35
  Besides the aforementioned languages, basic support can be expected for additional 91 languages that were used during
36
  the pretraining of the base model (see Appendix A of [XLM-R paper](https://arxiv.org/abs/1911.02116)).
 
111
  multilingual capacities. Note that not all training languages are part of the benchmark, so we only report the metrics
112
  for the existing languages.
113
 
114
+ | Language | NDCG@10 |
115
+ |:--------------------|--------:|
116
+ | German | 0.320 |
117
+ | Spanish | 0.418 |
118
+ | French | 0.382 |
119
+ | Japanese | 0.479 |
120
+ | Simplified Chinese | 0.414 |