Update README.md

README.md

@@ -1,132 +1,133 @@
 ---
 language: ar
+datasets:
+ - wikipedia
+ - OSIAN
+ - 1.5B Arabic Corpus
+widget:
+ - text: " عاصمة لبنان هي [MASK] ."
 ---
 
-# AraBERT : Pre-training BERT for Arabic Language Understanding
-<img src="https://github.com/aub-mind/arabert/blob/master/arabert_logo.png" width="100" align="left"/>  
+# !!! A newer version of this model is available !!! [AraBERTv2](https://huggingface.co/aubmindlab/bert-base-arabertv02)
 
-**AraBERT** is an Arabic pretrained lanaguage model based on [Google's BERT architechture](https://github.com/google-research/bert). AraBERT uses the same BERT-Base config. More details are available in the [AraBERT PAPER](https://arxiv.org/abs/2003.00104v2) and in the [AraBERT Meetup](https://github.com/WissamAntoun/pydata_khobar_meetup)
 
-There are two version off the model AraBERTv0.1 and AraBERTv1, with the difference being that AraBERTv1 uses pre-segmented text where prefixes and suffixes were split using the [Farasa Segmenter](http://alt.qcri.org/farasa/segmenter.html).
+# AraBERT v1 & v2 : Pre-training BERT for Arabic Language Understanding
 
-The model was trained on ~70M sentences or ~23GB of Arabic text with ~3B words. The training corpora are a collection of publically available large scale raw arabic text ([Arabic Wikidumps](https://archive.org/details/arwiki-20190201), [The 1.5B words Arabic Corpus](https://www.semanticscholar.org/paper/1.5-billion-words-Arabic-Corpus-El-Khair/f3eeef4afb81223df96575adadf808fe7fe440b4), [The OSIAN Corpus](https://www.aclweb.org/anthology/W19-4619), Assafir news articles, and 4 other manually crawled news websites (Al-Akhbar, Annahar, AL-Ahram, AL-Wafd) from [the Wayback Machine](http://web.archive.org/))
+<img src="https://raw.githubusercontent.com/aub-mind/arabert/master/arabert_logo.png" width="100" align="left"/>
 
-We evalaute both AraBERT models on different downstream tasks and compare it to [mBERT]((https://github.com/google-research/bert/blob/master/multilingual.md)), and other state of the art models (*To the extent of our knowledge*). The Tasks were Sentiment Analysis on 6 different datasets ([HARD](https://github.com/elnagara/HARD-Arabic-Dataset), [ASTD-Balanced](https://www.aclweb.org/anthology/D15-1299), [ArsenTD-Lev](https://staff.aub.edu.lb/~we07/Publications/ArSentD-LEV_Sentiment_Corpus.pdf), [LABR](https://github.com/mohamedadaly/LABR), [ArSaS](http://lrec-conf.org/workshops/lrec2018/W30/pdf/22_W30.pdf)), Named Entity Recognition with the [ANERcorp](http://curtis.ml.cmu.edu/w/courses/index.php/ANERcorp), and Arabic Question Answering on [Arabic-SQuAD and ARCD](https://github.com/husseinmozannar/SOQAL)
+**AraBERT** is an Arabic pretrained lanaguage model based on [Google's BERT architechture](https://github.com/google-research/bert). AraBERT uses the same BERT-Base config. More details are available in the [AraBERT Paper](https://arxiv.org/abs/2003.00104) and in the [AraBERT Meetup](https://github.com/WissamAntoun/pydata_khobar_meetup)
 
-**Update 2 (21/5/2020) :**
-Added support for the farasapy segmenter https://github.com/MagedSaeed/farasapy in the ``preprocess_arabert.py`` which is ~6x faster than the ``py4j.java_gateway``, consider setting ``use_farasapy=True`` when calling preprocess and pass it an instance of ``FarasaSegmenter(interactive=True)`` with interactive set to ``True`` for faster segmentation.
+There are two versions of the model, AraBERTv0.1 and AraBERTv1, with the difference being that AraBERTv1 uses pre-segmented text where prefixes and suffixes were splitted using the [Farasa Segmenter](http://alt.qcri.org/farasa/segmenter.html).
 
-**Update 1 (21/4/2020) :** 
-Fixed an issue with ARCD fine-tuning which drastically improved performance. Initially we didn't account for the change of the ```answer_start``` during preprocessing.
-## Results (Acc.)
-Task | prev. SOTA | mBERT | AraBERTv0.1 | AraBERTv1
----|:---:|:---:|:---:|:---:
-HARD |95.7 [ElJundi et.al.](https://www.aclweb.org/anthology/W19-4608/)|95.7|**96.2**|96.1
-ASTD |86.5 [ElJundi et.al.](https://www.aclweb.org/anthology/W19-4608/)| 80.1|92.2|**92.6**
-ArsenTD-Lev|52.4 [ElJundi et.al.](https://www.aclweb.org/anthology/W19-4608/)|51|58.9|**59.4**
-AJGT|93 [Dahou et.al.](https://dl.acm.org/doi/fullHtml/10.1145/3314941)| 83.6|93.1|**93.8**
-LABR|**87.5** [Dahou et.al.](https://dl.acm.org/doi/fullHtml/10.1145/3314941)|83|85.9|86.7
-ANERcorp|81.7 (BiLSTM-CRF)|78.4|**84.2**|81.9
-ARCD|mBERT|EM:34.2 F1: 61.3|EM:51.14 F1:82.13|**EM:54.84 F1: 82.15**
 
-*If you tested AraBERT on a public dataset and you want to add your results to the table above, open a pull request or contact us. Also make sure to have your code available online so we can add it as a reference*
+We evalaute AraBERT models on different downstream tasks and compare them to [mBERT]((https://github.com/google-research/bert/blob/master/multilingual.md)), and other state of the art models (*To the extent of our knowledge*). The Tasks were Sentiment Analysis on 6 different datasets ([HARD](https://github.com/elnagara/HARD-Arabic-Dataset), [ASTD-Balanced](https://www.aclweb.org/anthology/D15-1299), [ArsenTD-Lev](https://staff.aub.edu.lb/~we07/Publications/ArSentD-LEV_Sentiment_Corpus.pdf), [LABR](https://github.com/mohamedadaly/LABR)), Named Entity Recognition with the [ANERcorp](http://curtis.ml.cmu.edu/w/courses/index.php/ANERcorp), and Arabic Question Answering on [Arabic-SQuAD and ARCD](https://github.com/husseinmozannar/SOQAL)
 
-## How to use
+# AraBERTv2
 
-You can easily use AraBERT since it is almost fully compatible with existing codebases (Use this repo instead of the official BERT one, the only difference is in the ```tokenization.py``` file where we modify the _is_punctuation function to make it compatible with the "+" symbol and the "[" and "]" characters)
+## What's New!
 
-To use HuggingFace's Transformer repository you only need to provide a list of token that forces the model to not split them, also make sure that the text is pre-segmented:
-**Not all libraries built on top of transformers support the `never_split` argument**
-```python
-from transformers import AutoTokenizer, AutoModel
-from arabert.preprocess_arabert import never_split_tokens, preprocess
-from farasa.segmenter import FarasaSegmenter
-
-arabert_tokenizer = AutoTokenizer.from_pretrained(
-    "aubmindlab/bert-base-arabert",
-    do_lower_case=False,
-    do_basic_tokenize=True,
-    never_split=never_split_tokens)
-arabert_model = AutoModel.from_pretrained("aubmindlab/bert-base-arabert")
-
-#Preprocess the text to make it compatible with AraBERT using farasapy
-farasa_segmenter = FarasaSegmenter(interactive=True)
-
-#or you can use a py4j JavaGateway to the farasa Segmneter .jar but it's slower 
-#(see update 2)
-#from py4j.java_gateway import JavaGateway
-#gateway = JavaGateway.launch_gateway(classpath='./PATH_TO_FARASA/FarasaSegmenterJar.jar')
-#farasa = gateway.jvm.com.qcri.farasa.segmenter.Farasa()
+AraBERT now comes in 4 new variants to replace the old v1 versions:
 
-text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
-text_preprocessed = preprocess( text,
-                                do_farasa_tokenization = True,
-                                farasa = farasa_segmenter,
-                                use_farasapy = True)
+More Detail in the AraBERT folder and in the [README](https://github.com/aub-mind/arabert/blob/master/AraBERT/README.md) and in the [AraBERT Paper](https://arxiv.org/abs/2003.00104v2)
 
->>>text_preprocessed: "و+ لن نبالغ إذا قل +نا إن هاتف أو كمبيوتر ال+ مكتب في زمن +نا هذا ضروري"
+ Model | HuggingFace Model Name | Size (MB/Params)| Pre-Segmentation | DataSet (Sentences/Size/nWords) |
+ ---|:---:|:---:|:---:|:---:
+AraBERTv0.2-base | [bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) | 543MB / 136M | No | 200M / 77GB / 8.6B |
+ AraBERTv0.2-large| [bert-large-arabertv02](https://huggingface.co/aubmindlab/bert-large-arabertv02) | 1.38G 371M | No | 200M / 77GB / 8.6B |
+AraBERTv2-base| [bert-base-arabertv2](https://huggingface.co/aubmindlab/bert-base-arabertv2) | 543MB 136M | Yes | 200M / 77GB / 8.6B |
+AraBERTv2-large| [bert-large-arabertv2](https://huggingface.co/aubmindlab/bert-large-arabertv2) | 1.38G 371M | Yes | 200M / 77GB / 8.6B |
+ AraBERTv0.1-base| [bert-base-arabertv01](https://huggingface.co/aubmindlab/bert-base-arabertv01) | 543MB 136M | No | 77M / 23GB / 2.7B |
+AraBERTv1-base| [bert-base-arabert](https://huggingface.co/aubmindlab/bert-base-arabert) | 543MB 136M | Yes | 77M / 23GB / 2.7B |
 
-arabert_tokenizer.tokenize(text_preprocessed)
+All models are available in the `HuggingFace` model page under the [aubmindlab](https://huggingface.co/aubmindlab/) name. Checkpoints are available in PyTorch, TF2 and TF1 formats.
 
->>> ['و+', 'لن', 'نبال', '##غ', 'إذا', 'قل', '+نا', 'إن', 'هاتف', 'أو', 'كمبيوتر', 'ال+', 'مكتب', 'في', 'زمن', '+نا', 'هذا', 'ضروري']
-```
+## Better Pre-Processing and New Vocab
 
-**AraBERTv0.1 is compatible with all existing libraries, since it needs no pre-segmentation.**
-```python
-from transformers import AutoTokenizer, AutoModel
+We identified an issue with AraBERTv1's wordpiece vocabulary. The issue came from punctuations and numbers that were still attached to words when learned the wordpiece vocab. We now insert a space between numbers and characters and around punctuation characters.
 
-arabert_tokenizer = AutoTokenizer.from_pretrained("aubmindlab/bert-base-arabertv01",do_lower_case=False)
-arabert_model = AutoModel.from_pretrained("aubmindlab/bert-base-arabertv01")
+The new vocabulary was learnt using the `BertWordpieceTokenizer` from the `tokenizers` library, and should now support the Fast tokenizer implementation from the `transformers` library.
 
-text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
-arabert_tokenizer.tokenize(text)
+**P.S.**: All the old BERT codes should work with the new BERT, just change the model name and check the new preprocessing dunction
+**Please read the section on how to use the [preprocessing function](#Preprocessing)**
 
->>> ['ولن', 'ن', '##بالغ', 'إذا', 'قلنا', 'إن', 'هاتف', 'أو', 'كمبيوتر', 'المكتب', 'في', 'زمن', '##ن', '##ا', 'هذا', 'ضروري']
-```
+## Bigger Dataset and More Compute
 
+We used ~3.5 times more data, and trained for longer.
+For Dataset Sources see the [Dataset Section](#Dataset)
 
-The ```araBERT_(Updated_Demo_TF).ipynb``` Notebook is a small demo using the AJGT dataset using TensorFlow (GPU and TPU compatible).
+Model | Hardware | num of examples with seq len (128 / 512) |128 (Batch Size/ Num of Steps) | 512 (Batch Size/ Num of Steps) | Total Steps | Total Time (in Days) |
+ ---|:---:|:---:|:---:|:---:|:---:|:---:
+AraBERTv0.2-base | TPUv3-8 | 420M / 207M |2560 / 1M | 384/ 2M | 3M | -
+AraBERTv0.2-large | TPUv3-128 | 420M / 207M | 13440 / 250K | 2056 / 300K | 550K | -
+AraBERTv2-base | TPUv3-8 | 520M / 245M |13440 / 250K | 2056 / 300K | 550K | -
+AraBERTv2-large | TPUv3-128 | 520M / 245M | 13440 / 250K | 2056 / 300K | 550K | -
+AraBERT-base (v1/v0.1) | TPUv2-8 | - |512 / 900K | 128 / 300K| 1.2M | 4 days
 
-**Coming Soon :** Fine-tunning demo using HuggingFace's Trainer API
+# Dataset
 
-**AraBERT on ARCD**
-During the preprocessing step the ```answer_start``` character position needs to be recalculated. You can use the file ```arcd_preprocessing.py``` as shown below to clean, preprocess the ARCD dataset before running ```run_squad.py```. More detailed Colab notebook is available in the [SOQAL repo](https://github.com/husseinmozannar/SOQAL).
-```bash
-python arcd_preprocessing.py \
-    --input_file="/PATH_TO/arcd-test.json" \
-    --output_file="arcd-test-pre.json" \
-    --do_farasa_tokenization=True \
-    --use_farasapy=True \
+The pretraining data used for the new AraBERT model is also used for Arabic **GPT2 and ELECTRA**.
+
+The dataset consists of 77GB or 200,095,961 lines or 8,655,948,860 words or 82,232,988,358 chars (before applying Farasa Segmentation)
+
+For the new dataset we added the unshuffled OSCAR corpus, after we thoroughly filter it, to the previous dataset used in AraBERTv1 but with out the websites that we previously crawled:
+- OSCAR unshuffled and filtered.
+- [Arabic Wikipedia dump](https://archive.org/details/arwiki-20190201) from 2020/09/01
+- [The 1.5B words Arabic Corpus](https://www.semanticscholar.org/paper/1.5-billion-words-Arabic-Corpus-El-Khair/f3eeef4afb81223df96575adadf808fe7fe440b4)
+- [The OSIAN Corpus](https://www.aclweb.org/anthology/W19-4619)
+- Assafir news articles. Huge thank you for Assafir for giving us the data
+
+# Preprocessing
+
+It is recommended to apply our preprocessing function before training/testing on any dataset.
+**Install farasapy to segment text for AraBERT v1 & v2 `pip install farasapy`**
+
+```python
+from arabert.preprocess import ArabertPreprocessor
+
+model_name="bert-base-arabertv01"
+arabert_prep = ArabertPreprocessor(model_name=model_name, keep_emojis=True)
+
+text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
+arabert_prep.preprocess(text)
+```
+
+## Accepted_models
 ```
+bert-base-arabertv01
+bert-base-arabert
+bert-base-arabertv02
+bert-base-arabertv2
+bert-large-arabertv02
+bert-large-arabertv2
+araelectra-base
+aragpt2-base
+aragpt2-medium
+aragpt2-large
+aragpt2-mega
+```
+
+# TensorFlow 1.x models
+
+The TF1.x model are available in the HuggingFace models repo.
+You can download them as follows:
+- via git-lfs: clone all the models in a repo
 ```bash
-python SOQAL/bert/run_squad.py \
-  --vocab_file="/PATH_TO_PRETRAINED_TF_CKPT/vocab.txt" \
-  --bert_config_file="/PATH_TO_PRETRAINED_TF_CKPT/config.json" \
-  --init_checkpoint="/PATH_TO_PRETRAINED_TF_CKPT/" \
-  --do_train=True \
-  --train_file=turk_combined_all_pre.json \
-  --do_predict=True \
-  --predict_file=arcd-test-pre.json \
-  --train_batch_size=32 \
-  --predict_batch_size=24 \
-  --learning_rate=3e-5 \
-  --num_train_epochs=4 \
-  --max_seq_length=384 \
-  --doc_stride=128 \
-  --do_lower_case=False\
-  --output_dir="/PATH_TO/OUTPUT_PATH"/ \
-  --use_tpu=True \
-  --tpu_name=$TPU_ADDRESS \
+curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
+sudo apt-get install git-lfs
+git lfs install
+git clone https://huggingface.co/aubmindlab/MODEL_NAME
+tar -C ./MODEL_NAME -zxvf /content/MODEL_NAME/tf1_model.tar.gz
 ```
-## Model Weights and Vocab Download
-Models | AraBERTv0.1 | AraBERTv1
----|:---:|:---:
-TensorFlow|[Drive Link](https://drive.google.com/open?id=1-kVmTUZZ4DP2rzeHNjTPkY8OjnQCpomO) | [Drive Link](https://drive.google.com/open?id=1-d7-9ljKgDJP5mx73uBtio-TuUZCqZnt)
-PyTorch| [Drive_Link](https://drive.google.com/open?id=1-_3te42mQCPD8SxwZ3l-VBL7yaJH-IOv)| [Drive_Link](https://drive.google.com/open?id=1-69s6Pxqbi63HOQ1M9wTcr-Ovc6PWLLo)
+where `MODEL_NAME` is any model under the `aubmindlab` name
 
-**You can find the PyTorch models in HuggingFace's Transformer Library under the ```aubmindlab``` username**
+- via `wget`:
+    - Go to the tf1_model.tar.gz file on huggingface.co/models/aubmindlab/MODEL_NAME.
+    - copy the `oid sha256`
+    - then run `wget  https://cdn-lfs.huggingface.co/aubmindlab/aragpt2-base/INSERT_THE_SHA_HERE` (ex: for `aragpt2-base`: `wget https://cdn-lfs.huggingface.co/aubmindlab/aragpt2-base/3766fc03d7c2593ff2fb991d275e96b81b0ecb2098b71ff315611d052ce65248`)
 
-## If you used this model please cite us as:
+
+# If you used this model please cite us as :
+Google Scholar has our Bibtex wrong (missing name), use this instead
 ```
 @inproceedings{antoun2020arabert,
   title={AraBERT: Transformer-based Model for Arabic Language Understanding},
@@ -135,10 +136,12 @@ PyTorch| [Drive_Link](https://drive.google.com/open?id=1-_3te42mQCPD8SxwZ3l-VBL7
   pages={9}
 }
 ```
-## Acknowledgments 
+# Acknowledgments
 Thanks to TensorFlow Research Cloud (TFRC) for the free access to Cloud TPUs, couldn't have done it without this program, and to the [AUB MIND Lab](https://sites.aub.edu.lb/mindlab/) Members for the continous support. Also thanks to [Yakshof](https://www.yakshof.com/#/) and Assafir for data and storage access. Another thanks for Habib Rahal (https://www.behance.net/rahalhabib), for putting a face to AraBERT.
 
-## Contacts
-**Wissam Antoun**: [Linkedin](https://www.linkedin.com/in/giulio-ravasio-3a81a9110/) | [Twitter](https://twitter.com/wissam_antoun) | [Github](https://github.com/WissamAntoun) | <wfa07@mail.aub.edu> | <wissam.antoun@gmail.com>
+# Contacts
+**Wissam Antoun**: [Linkedin](https://www.linkedin.com/in/wissam-antoun-622142b4/) | [Twitter](https://twitter.com/wissam_antoun) | [Github](https://github.com/WissamAntoun) | <wfa07@mail.aub.edu> | <wissam.antoun@gmail.com>
 
 **Fady Baly**: [Linkedin](https://www.linkedin.com/in/fadybaly/) | [Twitter](https://twitter.com/fadybaly) | [Github](https://github.com/fadybaly) | <fgb06@mail.aub.edu> | <baly.fady@gmail.com>
+
+