Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,25 @@ widget:
|
|
| 7 |
**ARABERT COVID-19** is a pretrained (fine-tuned) version of the AraBERT v2 model (https://huggingface.co/aubmindlab/bert-base-arabertv02). The pretraining was done using 1.5 million multi-dialect Arabic tweets regarding the COVID-19 pandemic from the “Large Arabic Twitter Dataset on COVID-19” (https://arxiv.org/abs/2004.04315).
|
| 8 |
The model can achieve better results for the tasks that deal with multi-dialect Arabic tweets in relation to the COVID-19 pandemic.
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
# Preprocessing
|
| 12 |
|
|
|
|
| 7 |
**ARABERT COVID-19** is a pretrained (fine-tuned) version of the AraBERT v2 model (https://huggingface.co/aubmindlab/bert-base-arabertv02). The pretraining was done using 1.5 million multi-dialect Arabic tweets regarding the COVID-19 pandemic from the “Large Arabic Twitter Dataset on COVID-19” (https://arxiv.org/abs/2004.04315).
|
| 8 |
The model can achieve better results for the tasks that deal with multi-dialect Arabic tweets in relation to the COVID-19 pandemic.
|
| 9 |
|
| 10 |
+
# Classification results for multiple fake-news detection tasks with and without using the arabert_c19:
|
| 11 |
+
For more details refer to the paper (link)
|
| 12 |
+
|
| 13 |
+
| | \multicolumn{5}{c}{Without Fine-tuning} | \multicolumn{5}{c}{With Fine-tuning} |
|
| 14 |
+
|------------------------------------|-----------------------------------------|------------------------------------------------|
|
| 15 |
+
| | \multicolumn{3}{c}{Baseline models} | \multicolumn{2}{c}{Pretrained Covid-19 models} | \multicolumn{3}{c}{Baseline models} | \multicolumn{2}{c}{Pretrained Covid-19 models} |
|
| 16 |
+
| | arabert | mbert | distilbert-multi | \textbf{arabert Cov19} | \textbf{mbert Cov19} | arabert | mbert | distilbert-multi | \textbf{arabert Cov19} | \textbf{mbert Cov19} |
|
| 17 |
+
| \textbf{Contains hate} | 0.8346 | 0.6675 | 0.7145 | \textbf{0.8649} | 0.8492 | 0.9809 | 0.97 | 0.9736 | \textbf{0.9858} | 0.9809 |
|
| 18 |
+
| \textbf{Talk about a cure} | 0.8193 | 0.7406 | 0.7127 | 0.9055 | \textbf{0.9176} | 0.99 | 0.9854 | 0.9774 | \textbf{0.9930} | 0.9904 |
|
| 19 |
+
| \textbf{Give advice} | 0.8287 | 0.6865 | 0.6974 | \textbf{0.9035} | 0.8948 | 0.9793 | 0.9664 | 0.9764 | 0.9824 | \textbf{0.9862} |
|
| 20 |
+
| \textbf{Rise moral } | 0.8398 | 0.7075 | 0.7049 | \textbf{0.8903} | 0.8838 | 0.9618 | 0.9663 | 0.9618 | 0.97 | \textbf{0.9712} |
|
| 21 |
+
| \textbf{News or opinion } | 0.8987 | 0.8332 | 0.8099 | \textbf{0.9163} | 0.9116 | 0.9552 | 0.9409 | 0.9529 | \textbf{0.9627} | 0.9594 |
|
| 22 |
+
| \textbf{Dialect} | 0.7533 | 0.558 | 0.5433 | \textbf{0.8230} | 0.7682 | 0.9266 | 0.9137 | 0.9102 | 0.9281 | \textbf{0.9317} |
|
| 23 |
+
| \textbf{Blame and negative speech} | 0.7426 | 0.597 | 0.6221 | \textbf{0.7997} | 0.7794 | 0.9607 | 0.9476 | 0.9587 | \textbf{0.9653} | 0.9633 |
|
| 24 |
+
| \textbf{Factual} | 0.9217 | 0.8427 | 0.8383 | 0.9575 | \textbf{0.9608} | 0.9958 | 0.9917 | 0.9925 | 0.995 | \textbf{0.9967} |
|
| 25 |
+
| \textbf{Worth fact-checking} | 0.7731 | 0.5298 | 0.5413 | 0.8265 | \textbf{0.8383} | 0.9885 | 0.9824 | 0.9763 | \textbf{0.9907} | 0.9891 |
|
| 26 |
+
| \textbf{Contains fake information} | 0.6415 | 0.5428 | 0.4743 | \textbf{0.7739} | 0.7228 | 0.9417 | 0.9353 | 0.9288 | \textbf{0.9578} | 0.9491 |
|
| 27 |
+
|
| 28 |
+
|
| 29 |
|
| 30 |
# Preprocessing
|
| 31 |
|