Commit ·
24d8940
1
Parent(s): d11be47
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,18 +2,51 @@
|
|
| 2 |
tags:
|
| 3 |
- generated_from_keras_callback
|
| 4 |
model-index:
|
| 5 |
-
- name:
|
| 6 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 10 |
probably proofread and complete it, then remove this comment. -->
|
| 11 |
|
| 12 |
-
#
|
| 13 |
|
| 14 |
-
This model
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -43,4 +76,4 @@ The following hyperparameters were used during training:
|
|
| 43 |
|
| 44 |
- Transformers 4.28.1
|
| 45 |
- TensorFlow 2.12.0
|
| 46 |
-
- Tokenizers 0.13.3
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_keras_callback
|
| 4 |
model-index:
|
| 5 |
+
- name: arabert-sarcasm-detector
|
| 6 |
results: []
|
| 7 |
+
license: afl-3.0
|
| 8 |
+
language:
|
| 9 |
+
- ar
|
| 10 |
+
metrics:
|
| 11 |
+
- accuracy
|
| 12 |
+
- F1 score
|
| 13 |
+
- precession
|
| 14 |
+
- recall
|
| 15 |
+
pipeline_tag: text-classification
|
| 16 |
+
widget:
|
| 17 |
+
- text: "العلم نور و الجهل ضلال"
|
| 18 |
+
example_title: "NS 01"
|
| 19 |
+
- text: " .جمع كلمة امراءة هي كلمة نساء"
|
| 20 |
+
example_title: "NS 02"
|
| 21 |
+
- text: ".للجامعة العربية موقفا كبيرا"
|
| 22 |
+
example_title: "NS 03"
|
| 23 |
+
- text: "شهر أكتوبر ده شهر عسل بجد مبيجبش ليا فيه غير الاكتئاب كل سنه"
|
| 24 |
+
example_title: "Sarc 01"
|
| 25 |
+
- text: " !جمع كلمة امراءة هي نساء!!! :):) حتى اللغة العربية مش قادرة عليهم "
|
| 26 |
+
example_title: "Sarc 02"
|
| 27 |
+
- text: " 🙂🙂جامعة العربية موقفا كبيرا يتسع لاكثر من الف سيارة !!!!!!!!"
|
| 28 |
+
example_title: "Sarc 03"
|
| 29 |
+
- text: " فى ناس زى النسكافيه ثلاثة فى واحد يتكلموا معاك وعنك وعليك"
|
| 30 |
+
example_title: "Sarc 04"
|
| 31 |
+
- text: "!!هو أنت كدة عايش؟ يا بني دا أنت ميت بالحياة"
|
| 32 |
+
example_title: "Sarc 05"
|
| 33 |
---
|
| 34 |
|
| 35 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 36 |
probably proofread and complete it, then remove this comment. -->
|
| 37 |
|
| 38 |
+
# arabert-sarcasm-detector
|
| 39 |
|
| 40 |
+
This model is fine-tuned aubmindlab/bert-base-arabertv02-twitter was Fintuned on ArSarcasT dataset.
|
| 41 |
It achieves the following results on the evaluation set:
|
| 42 |
|
| 43 |
+
| Eval Datatset| Accuracy | F1 | Precession | Recall|
|
| 44 |
+
| :----- | :---: | :---: | :---: | :---: |
|
| 45 |
+
|ArSarcasT |0.831 | 0.716 | 0.727 | 0.705 |
|
| 46 |
+
|iSarcasmEVAL |0.886 | 0.619 | 0.591 | 0.650 |
|
| 47 |
+
|AraSarcasmV2 |0.765 | 0.553 | 0.577 | 0.532 |
|
| 48 |
+
|IDAT |0.796 | 0.794 | 0.769 | 0.821 |
|
| 49 |
+
|
| 50 |
|
| 51 |
## Model description
|
| 52 |
|
|
|
|
| 76 |
|
| 77 |
- Transformers 4.28.1
|
| 78 |
- TensorFlow 2.12.0
|
| 79 |
+
- Tokenizers 0.13.3
|