go-inoue commited on
Commit
b129f39
1 Parent(s): b9c09ae

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ar
4
+ license: apache-2.0
5
+ widget:
6
+ - text: 'عامل ايه ؟'
7
+ ---
8
+ # CAMeLBERT-CA POS-EGY Model
9
+ ## Model description
10
+ **CAMeLBERT-CA POS-EGY Model** is a Egyptian Arabic POS tagging model that was built by fine-tuning the [CAMeLBERT-CA](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-ca/) model.
11
+ For the fine-tuning, we used the ARZTB dataset .
12
+ Our fine-tuning procedure and the hyperparameters we used can be found in our paper *"[The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models](https://arxiv.org/abs/2103.06678)."* Our fine-tuning code can be found [here](https://github.com/CAMeL-Lab/CAMeLBERT).
13
+
14
+ ## Intended uses
15
+ You can use the CAMeLBERT-CA POS-EGY model as part of the transformers pipeline.
16
+ This model will also be available in [CAMeL Tools](https://github.com/CAMeL-Lab/camel_tools) soon.
17
+
18
+ #### How to use
19
+ To use the model with a transformers pipeline:
20
+ ```python
21
+ >>> from transformers import pipeline
22
+ >>> pos = pipeline('token-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-ca-pos-egy')
23
+ >>> text = 'عامل ايه ؟'
24
+ >>> pos(text)
25
+ [{'entity': 'adj', 'score': 0.9990943, 'index': 1, 'word': 'عامل', 'start': 0, 'end': 4}, {'entity': 'pron_interrog', 'score': 0.99863535, 'index': 2, 'word': 'ايه', 'start': 5, 'end': 8}, {'entity': 'punc', 'score': 0.99990875, 'index': 3, 'word': '؟', 'start': 9, 'end': 10}]
26
+ ```
27
+ *Note*: to download our models, you would need `transformers>=3.5.0`.
28
+ Otherwise, you could download the models manually.
29
+ ## Citation
30
+ ```bibtex
31
+ @inproceedings{inoue-etal-2021-interplay,
32
+ title = "The Interplay of Variant, Size, and Task Type in {A}rabic Pre-trained Language Models",
33
+ author = "Inoue, Go and
34
+ Alhafni, Bashar and
35
+ Baimukan, Nurpeiis and
36
+ Bouamor, Houda and
37
+ Habash, Nizar",
38
+ booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
39
+ month = apr,
40
+ year = "2021",
41
+ address = "Kyiv, Ukraine (Online)",
42
+ publisher = "Association for Computational Linguistics",
43
+ abstract = "In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: Modern Standard Arabic (MSA), dialectal Arabic, and classical Arabic, in addition to a fourth language model which is pre-trained on a mix of the three. We also examine the importance of pre-training data size by building additional models that are pre-trained on a scaled-down set of the MSA variant. We compare our different models to each other, as well as to eight publicly available models by fine-tuning them on five NLP tasks spanning 12 datasets. Our results suggest that the variant proximity of pre-training data to fine-tuning data is more important than the pre-training data size. We exploit this insight in defining an optimized system selection model for the studied tasks.",
44
+ }
45
+ ```