m3hrdadfi commited on
Commit
8c5d0be
1 Parent(s): 89223b9

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: fa
3
+ license: apache-2.0
4
+ ---
5
+
6
+ # ParsBERT (v2.0)
7
+ A Transformer-based Model for Persian Language Understanding
8
+
9
+ We reconstructed the vocabulary and fine-tuned the ParsBERT v1.1 on the new Persian corpora in order to provide some functionalities for using ParsBERT in other scopes!
10
+ Please follow the [ParsBERT](https://github.com/hooshvare/parsbert) repo for the latest information about previous and current models.
11
+
12
+
13
+ ## Persian Sentiment [Digikala, SnappFood, DeepSentiPers]
14
+
15
+ It aims to classify text, such as comments, based on their emotional bias. We tested three well-known datasets for this task: `Digikala` user comments, `SnappFood` user comments, and `DeepSentiPers` in two binary-form and multi-form types.
16
+
17
+
18
+
19
+ ### SnappFood
20
+
21
+ [Snappfood](https://snappfood.ir/) (an online food delivery company) user comments containing 70,000 comments with two labels (i.e. polarity classification):
22
+
23
+ 1. Happy
24
+ 2. Sad
25
+
26
+ | Label | # |
27
+ |:--------:|:-----:|
28
+ | Negative | 35000 |
29
+ | Positive | 35000 |
30
+
31
+ **Download**
32
+ You can download the dataset from [here](https://drive.google.com/uc?id=15J4zPN1BD7Q_ZIQ39VeFquwSoW8qTxgu)
33
+
34
+ ## Results
35
+
36
+ The following table summarizes the F1 score obtained by ParsBERT as compared to other models and architectures.
37
+
38
+ | Dataset | ParsBERT v2 | ParsBERT v1 | mBERT | DeepSentiPers |
39
+ |:------------------------:|:-----------:|:-----------:|:-----:|:-------------:|
40
+ | SnappFood User Comments | 87.98 | 88.12* | 87.87 | - |
41
+
42
+
43
+ ## How to use :hugs:
44
+
45
+ | Task | Notebook |
46
+ |---------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
47
+ | Sentiment Analysis | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/hooshvare/parsbert/blob/master/notebooks/Taaghche_Sentiment_Analysis.ipynb) |
48
+
49
+
50
+ ### BibTeX entry and citation info
51
+
52
+ Please cite in publications as the following:
53
+
54
+ ```bibtex
55
+ @article{ParsBERT,
56
+ title={ParsBERT: Transformer-based Model for Persian Language Understanding},
57
+ author={Mehrdad Farahani, Mohammad Gharachorloo, Marzieh Farahani, Mohammad Manthouri},
58
+ journal={ArXiv},
59
+ year={2020},
60
+ volume={abs/2005.12515}
61
+ }
62
+ ```
63
+
64
+ ## Questions?
65
+ Post a Github issue on the [ParsBERT Issues](https://github.com/hooshvare/parsbert/issues) repo.