vukosi commited on
Commit
61dfc25
1 Parent(s): 9da34bb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -1
README.md CHANGED
@@ -8,4 +8,70 @@ metrics:
8
  - f1
9
  library_name: transformers
10
  pipeline_tag: token-classification
11
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  - f1
9
  library_name: transformers
10
  pipeline_tag: token-classification
11
+ ---
12
+ # PuoBERTa-NER: A Setswana Langage Model Finetuned on MasakhaNER-2 for Named Entity Recognition.
13
+
14
+ A Roberta-based language model finetuned on MasakhaneNER-2 for Named Entity Recognition.
15
+
16
+ Based on [https://huggingface.co/dsfsi/PuoBERTa](https://huggingface.co/dsfsi/PuoBERTa)
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ This is a POS model trained on Setswana based on PuoBERTa and fineruned on MasakhaNER-2 Setswana.
23
+
24
+ - **Developed by:** Vukosi Marivate ([@vukosi](https://huggingface.co/@vukosi)), Moseli Mots'Oehli ([@MoseliMotsoehli](https://huggingface.co/@MoseliMotsoehli)) , Valencia Wagner, Richard Lastrucci and Isheanesu Dzingirai
25
+ - **Model type:** RoBERTa Model
26
+ - **Language(s) (NLP):** Setswana
27
+ - **License:** CC BY 4.0
28
+
29
+ ### Model Performance
30
+
31
+ Performance of models on the [MasakhaNER-2](https://github.com/masakhane-io/masakhane-ner/tree/main/MasakhaNER2.0) downstream task.
32
+
33
+ | Model | Test Performance (f1 score) |
34
+ |---|---|
35
+ | **Multilingual Models** | |
36
+ | AfriBERTa | 83.2 |
37
+ | AfroXLMR-base | 87.7 |
38
+ | AfroXLMR-large | 89.4 |
39
+ | **Monolingual Models** | |
40
+ | NCHLT TSN RoBERTa | 74.2 |
41
+ | PuoBERTa | **78.2** |
42
+ | PuoBERTa+JW300 | **80.2** |
43
+
44
+ ### Usage
45
+
46
+ Use this model for Part of Speech Tagging for Setswana.
47
+ ```python
48
+
49
+ ```
50
+
51
+ ## Citation Information
52
+
53
+ Bibtex Refrence
54
+
55
+ ```
56
+ @article{marivatePuoBERTa2023,
57
+ title={PuoBERTa: Training and evaluation of a curated language model for Setswana},
58
+ author={Vukosi Marivate and Moseli Mots'Oehli and Valencia Wagner and Richard Lastrucci and Isheanesu Dzingirai},
59
+ journal={ArXiv},
60
+ }
61
+ ```
62
+
63
+ ## Contributing
64
+
65
+ Your contributions are welcome! Feel free to improve the model.
66
+
67
+ ## Model Card Authors
68
+
69
+ Vukosi Marivate
70
+
71
+ ## Model Card Contact
72
+
73
+ For more details, reach out or check our [website](https://dsfsi.github.io/).
74
+
75
+ Email: vukosi.marivate@cs.up.ac.za
76
+
77
+ **Enjoy exploring Setswana through AI!**