julien-c HF staff commited on
Commit
a3d8037
1 Parent(s): ef8d69b

Migrate model card from transformers-repo

Browse files

Read announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/HooshvareLab/bert-base-parsbert-armanner-uncased/README.md

Files changed (1) hide show
  1. README.md +124 -0
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## ParsBERT: Transformer-based Model for Persian Language Understanding
2
+
3
+ ParsBERT is a monolingual language model based on Google’s BERT architecture with the same configurations as BERT-Base.
4
+
5
+ Paper presenting ParsBERT: [arXiv:2005.12515](https://arxiv.org/abs/2005.12515)
6
+
7
+ All the models (downstream tasks) are uncased and trained with whole word masking. (coming soon stay tuned)
8
+
9
+
10
+ ## Persian NER [ARMAN, PEYMA, ARMAN+PEYMA]
11
+
12
+ This task aims to extract named entities in the text, such as names and label with appropriate `NER` classes such as locations, organizations, etc. The datasets used for this task contain sentences that are marked with `IOB` format. In this format, tokens that are not part of an entity are tagged as `”O”` the `”B”`tag corresponds to the first word of an object, and the `”I”` tag corresponds to the rest of the terms of the same entity. Both `”B”` and `”I”` tags are followed by a hyphen (or underscore), followed by the entity category. Therefore, the NER task is a multi-class token classification problem that labels the tokens upon being fed a raw text. There are two primary datasets used in Persian NER, `ARMAN`, and `PEYMA`. In ParsBERT, we prepared ner for both datasets as well as a combination of both datasets.
13
+
14
+
15
+
16
+ ### PEYMA
17
+
18
+ PEYMA dataset includes 7,145 sentences with a total of 302,530 tokens from which 41,148 tokens are tagged with seven different classes.
19
+
20
+ 1. Organization
21
+ 2. Money
22
+ 3. Location
23
+ 4. Date
24
+ 5. Time
25
+ 6. Person
26
+ 7. Percent
27
+
28
+
29
+ | Label | # |
30
+ |:------------:|:-----:|
31
+ | Organization | 16964 |
32
+ | Money | 2037 |
33
+ | Location | 8782 |
34
+ | Date | 4259 |
35
+ | Time | 732 |
36
+ | Person | 7675 |
37
+ | Percent | 699 |
38
+
39
+
40
+
41
+ **Download**
42
+ You can download the dataset from [here](http://nsurl.org/tasks/task-7-named-entity-recognition-ner-for-farsi/)
43
+
44
+ ---
45
+
46
+ ### ARMAN
47
+
48
+ ARMAN dataset holds 7,682 sentences with 250,015 sentences tagged over six different classes.
49
+
50
+ 1. Organization
51
+ 2. Location
52
+ 3. Facility
53
+ 4. Event
54
+ 5. Product
55
+ 6. Person
56
+
57
+
58
+ | Label | # |
59
+ |:------------:|:-----:|
60
+ | Organization | 30108 |
61
+ | Location | 12924 |
62
+ | Facility | 4458 |
63
+ | Event | 7557 |
64
+ | Product | 4389 |
65
+ | Person | 15645 |
66
+
67
+
68
+
69
+ **Download**
70
+ You can download the dataset from [here](https://github.com/HaniehP/PersianNER)
71
+
72
+
73
+
74
+ ## Results
75
+
76
+ The following table summarizes the F1 score obtained by ParsBERT as compared to other models and architectures.
77
+
78
+ | Dataset | ParsBERT | MorphoBERT | Beheshti-NER | LSTM-CRF | Rule-Based CRF | BiLSTM-CRF |
79
+ |:---------------:|:--------:|:----------:|:--------------:|:----------:|:----------------:|:------------:|
80
+ | ARMAN + PEYMA | 95.13* | - | - | - | - | - |
81
+ | PEYMA | 98.79* | - | 90.59 | - | 84.00 | - |
82
+ | ARMAN | 93.10* | 89.9 | 84.03 | 86.55 | - | 77.45 |
83
+
84
+
85
+ ## How to use :hugs:
86
+ | Notebook | Description | |
87
+ |:----------|:-------------|------:|
88
+ | [How to use Pipelines](https://github.com/hooshvare/parsbert-ner/blob/master/persian-ner-pipeline.ipynb) | Simple and efficient way to use State-of-the-Art models on downstream tasks through transformers | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/hooshvare/parsbert-ner/blob/master/persian-ner-pipeline.ipynb) |
89
+
90
+
91
+ ## Cite
92
+
93
+ Please cite the following paper in your publication if you are using [ParsBERT](https://arxiv.org/abs/2005.12515) in your research:
94
+
95
+ ```markdown
96
+ @article{ParsBERT,
97
+ title={ParsBERT: Transformer-based Model for Persian Language Understanding},
98
+ author={Mehrdad Farahani, Mohammad Gharachorloo, Marzieh Farahani, Mohammad Manthouri},
99
+ journal={ArXiv},
100
+ year={2020},
101
+ volume={abs/2005.12515}
102
+ }
103
+ ```
104
+
105
+
106
+ ## Acknowledgments
107
+
108
+ We hereby, express our gratitude to the [Tensorflow Research Cloud (TFRC) program](https://tensorflow.org/tfrc) for providing us with the necessary computation resources. We also thank [Hooshvare](https://hooshvare.com) Research Group for facilitating dataset gathering and scraping online text resources.
109
+
110
+
111
+ ## Contributors
112
+
113
+ - Mehrdad Farahani: [Linkedin](https://www.linkedin.com/in/m3hrdadfi/), [Twitter](https://twitter.com/m3hrdadfi), [Github](https://github.com/m3hrdadfi)
114
+ - Mohammad Gharachorloo: [Linkedin](https://www.linkedin.com/in/mohammad-gharachorloo/), [Twitter](https://twitter.com/MGharachorloo), [Github](https://github.com/baarsaam)
115
+ - Marzieh Farahani: [Linkedin](https://www.linkedin.com/in/marziehphi/), [Twitter](https://twitter.com/marziehphi), [Github](https://github.com/marziehphi)
116
+ - Mohammad Manthouri: [Linkedin](https://www.linkedin.com/in/mohammad-manthouri-aka-mansouri-07030766/), [Twitter](https://twitter.com/mmanthouri), [Github](https://github.com/mmanthouri)
117
+ - Hooshvare Team: [Official Website](https://hooshvare.com/), [Linkedin](https://www.linkedin.com/company/hooshvare), [Twitter](https://twitter.com/hooshvare), [Github](https://github.com/hooshvare), [Instagram](https://www.instagram.com/hooshvare/)
118
+
119
+ + And a special thanks to Sara Tabrizi for her fantastic poster design. Follow her on: [Linkedin](https://www.linkedin.com/in/sara-tabrizi-64548b79/), [Behance](https://www.behance.net/saratabrizi), [Instagram](https://www.instagram.com/sara_b_tabrizi/)
120
+
121
+ ## Releases
122
+
123
+ ### Release v0.1 (May 29, 2019)
124
+ This is the first version of our ParsBERT NER!