go-inoue commited on
Commit
ba8e927
1 Parent(s): 5acc0db

Create README.md

Browse files
Files changed (1) hide show
  1. RAEDME.md +50 -0
RAEDME.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ar
4
+ license: apache-2.0
5
+ widget:
6
+ - text: "أنا بخير"
7
+ ---
8
+ # CAMeLBERT Mix SA Model
9
+ ## Model description
10
+ **CAMeLBERT Mix SA Model** is a Sentiment Analysis (SA) model that was built by fine-tuning the [CAMeLBERT Mix](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-mix/) model.
11
+ For the fine-tuning, we used the [ASTD](https://aclanthology.org/D15-1299.pdf), [ArSAS](http://lrec-conf.org/workshops/lrec2018/W30/pdf/22_W30.pdf), and [SemEval](https://aclanthology.org/S17-2088.pdf) datasets.
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
+ ## Intended uses
14
+ You can use the CAMeLBERT Mix SA model directly as part of our [CAMeL Tools](https://github.com/CAMeL-Lab/camel_tools) SA component (*recommended*) or as part of the transformers pipeline.
15
+ #### How to use
16
+ To use the model with the [CAMeL Tools](https://github.com/CAMeL-Lab/camel_tools) SA component:
17
+ ```python
18
+ >>> from camel_tools.sentiment import SentimentAnalyzer
19
+ >>> sa = SentimentAnalyzer("CAMeL-Lab/bert-base-arabic-camelbert-mix-sentiment")
20
+ >>> sentences = ['أنا بخير', 'أنا لست بخير']
21
+ >>> sa.predict(sentences)
22
+ >>> ['positive', 'negative']
23
+ ```
24
+ You can also use the NER model directly with a transformers pipeline:
25
+ ```python
26
+ >>> from transformers import pipeline
27
+ >>> sa = pipeline('sentiment-analysis', model='CAMeL-Lab/bert-base-arabic-camelbert-mix-sentiment')
28
+ >>> sentences = ['أنا بخير', 'أنا لست بخير']
29
+ >>> sa(sentences)
30
+ [{'label': 'positive', 'score': 0.9616648554801941},
31
+ {'label': 'negative', 'score': 0.9779177904129028}]
32
+ ```
33
+ *Note*: to download our models, you would need `transformers>=3.5.0`. Otherwise, you could download the models
34
+ ## Citation
35
+ ```bibtex
36
+ @inproceedings{inoue-etal-2021-interplay,
37
+ title = "The Interplay of Variant, Size, and Task Type in {A}rabic Pre-trained Language Models",
38
+ author = "Inoue, Go and
39
+ Alhafni, Bashar and
40
+ Baimukan, Nurpeiis and
41
+ Bouamor, Houda and
42
+ Habash, Nizar",
43
+ booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
44
+ month = apr,
45
+ year = "2021",
46
+ address = "Kyiv, Ukraine (Online)",
47
+ publisher = "Association for Computational Linguistics",
48
+ 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.",
49
+ }
50
+ ```