Update README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ metrics:
|
|
20 |
pipeline_tag: text-classification
|
21 |
---
|
22 |
|
23 |
-
#
|
24 |
## Model description
|
25 |
**afrisenti-twitter-sentiment-afroxlmr-large** is the first multilingual twitter **sentiment classification** model for twelve (12) Nigerian languages (Amharic, Algerian Arabic, Darija, Hausa, Igbo, Kinyarwanda, Nigerian Pidgin, Mozambique Portuguese, Swahili, Tsonga, Twi, and Yorùbá) based on a fine-tuned castorini/afriberta_large large model.
|
26 |
It achieves the **state-of-the-art performance** for the twitter sentiment classification task trained on the [AfriSenti corpus](https://github.com/afrisenti-semeval/afrisent-semeval-2023).
|
@@ -63,13 +63,6 @@ This model is limited by its training dataset and domain i.e Twitter. This may n
|
|
63 |
|
64 |
## Training procedure
|
65 |
This model was trained on a single Nvidia A10 GPU with recommended hyperparameters from the [original AfriSenti paper](https://arxiv.org/abs/2302.08956).
|
66 |
-
## Eval results on Test set (F-score), average over 5 runs.
|
67 |
-
language|F1-score
|
68 |
-
-|-
|
69 |
-
hau |81.2
|
70 |
-
ibo |80.8
|
71 |
-
pcm |74.5
|
72 |
-
yor |80.4
|
73 |
|
74 |
### BibTeX entry and citation info
|
75 |
```
|
|
|
20 |
pipeline_tag: text-classification
|
21 |
---
|
22 |
|
23 |
+
# AfriSenti-twitter-sentiment-afroxlmr-large
|
24 |
## Model description
|
25 |
**afrisenti-twitter-sentiment-afroxlmr-large** is the first multilingual twitter **sentiment classification** model for twelve (12) Nigerian languages (Amharic, Algerian Arabic, Darija, Hausa, Igbo, Kinyarwanda, Nigerian Pidgin, Mozambique Portuguese, Swahili, Tsonga, Twi, and Yorùbá) based on a fine-tuned castorini/afriberta_large large model.
|
26 |
It achieves the **state-of-the-art performance** for the twitter sentiment classification task trained on the [AfriSenti corpus](https://github.com/afrisenti-semeval/afrisent-semeval-2023).
|
|
|
63 |
|
64 |
## Training procedure
|
65 |
This model was trained on a single Nvidia A10 GPU with recommended hyperparameters from the [original AfriSenti paper](https://arxiv.org/abs/2302.08956).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
### BibTeX entry and citation info
|
68 |
```
|