--- language: - ar license: apache-2.0 widget: - text: "الهدف من الحياة هو [MASK] ." --- # CAMeLBERT: A collection of pre-trained models for Arabic NLP tasks ## Model description **CAMeLBERT** is a collection of BERT models pre-trained on Arabic texts with different sizes and variants. We release pre-trained language models for Modern Standard Arabic (MSA), dialectal Arabic (DA), and classical Arabic (CA), in addition to a model pre-trained on a mix of the three. We also provide additional models that are pre-trained on a scaled-down set of the MSA variant (half, quarter, eighth, and sixteenth). The details are described in the paper *"[The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models](https://arxiv.org/abs/2103.06678)."* This model card describes **CAMeLBERT-DA** (`bert-base-camelbert-da`), a model pre-trained on the DA (dialectal Arabic) dataset. ||Model|Variant|Size|#Word| |-|-|:-:|-:|-:| ||`bert-base-camelbert-mix`|CA,DA,MSA|167GB|17.3B| ||`bert-base-camelbert-ca`|CA|6GB|847M| |✔|`bert-base-camelbert-da`|DA|54GB|5.8B| ||`bert-base-camelbert-msa`|MSA|107GB|12.6B| ||`bert-base-camelbert-msa-half`|MSA|53GB|6.3B| ||`bert-base-camelbert-msa-quarter`|MSA|27GB|3.1B| ||`bert-base-camelbert-msa-eighth`|MSA|14GB|1.6B| ||`bert-base-camelbert-msa-sixteenth`|MSA|6GB|746M| ## Intended uses You can use the released model for either masked language modeling or next sentence prediction. However, it is mostly intended to be fine-tuned on an NLP task, such as NER, POS tagging, sentiment analysis, dialect identification, and poetry classification. We release our fine-tuninig code [here](https://github.com/CAMeL-Lab/CAMeLBERT). #### How to use You can use this model directly with a pipeline for masked language modeling: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='CAMeL-Lab/bert-base-camelbert-da') >>> unmasker("الهدف من الحياة هو [MASK] .") [{'sequence': '[CLS] الهدف من الحياة هو.. [SEP]', 'score': 0.062508225440979, 'token': 18, 'token_str': '.'}, {'sequence': '[CLS] الهدف من الحياة هو الموت. [SEP]', 'score': 0.033172328025102615, 'token': 4295, 'token_str': 'الموت'}, {'sequence': '[CLS] الهدف من الحياة هو الحياة. [SEP]', 'score': 0.029575437307357788, 'token': 3696, 'token_str': 'الحياة'}, {'sequence': '[CLS] الهدف من الحياة هو الرحيل. [SEP]', 'score': 0.02724040113389492, 'token': 11449, 'token_str': 'الرحيل'}, {'sequence': '[CLS] الهدف من الحياة هو الحب. [SEP]', 'score': 0.01564178802073002, 'token': 3088, 'token_str': 'الحب'}] ``` *Note*: to download our models, you would need `transformers>=3.5.0`. Otherwise, you could download the models manually. Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained('CAMeL-Lab/bert-base-camelbert-da') model = AutoModel.from_pretrained('CAMeL-Lab/bert-base-camelbert-da') text = "مرحبا يا عالم." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) ``` and in TensorFlow: ```python from transformers import AutoTokenizer, TFAutoModel tokenizer = AutoTokenizer.from_pretrained('CAMeL-Lab/bert-base-camelbert-da') model = TFAutoModel.from_pretrained('CAMeL-Lab/bert-base-camelbert-da') text = "مرحبا يا عالم." encoded_input = tokenizer(text, return_tensors='tf') output = model(encoded_input) ``` ## Training data - DA (dialectal Arabic) - A collection of dialectal Arabic data described in [our paper](https://arxiv.org/abs/2103.06678). ## Training procedure We use [the original implementation](https://github.com/google-research/bert) released by Google for pre-training. We follow the original English BERT model's hyperparameters for pre-training, unless otherwise specified. ### Preprocessing - After extracting the raw text from each corpus, we apply the following pre-processing. - We first remove invalid characters and normalize white spaces using the utilities provided by [the original BERT implementation](https://github.com/google-research/bert/blob/eedf5716ce1268e56f0a50264a88cafad334ac61/tokenization.py#L286-L297). - We also remove lines without any Arabic characters. - We then remove diacritics and kashida using [CAMeL Tools](https://github.com/CAMeL-Lab/camel_tools). - Finally, we split each line into sentences with a heuristics-based sentence segmenter. - We train a WordPiece tokenizer on the entire dataset (167 GB text) with a vocabulary size of 30,000 using [HuggingFace's tokenizers](https://github.com/huggingface/tokenizers). - We do not lowercase letters nor strip accents. ### Pre-training - The model was trained on a single cloud TPU (`v3-8`) for one million steps in total. - The first 90,000 steps were trained with a batch size of 1,024 and the rest was trained with a batch size of 256. - The sequence length was limited to 128 tokens for 90% of the steps and 512 for the remaining 10%. - We use whole word masking and a duplicate factor of 10. - We set max predictions per sequence to 20 for the dataset with max sequence length of 128 tokens and 80 for the dataset with max sequence length of 512 tokens. - We use a random seed of 12345, masked language model probability of 0.15, and short sequence probability of 0.1. - The optimizer used is Adam with a learning rate of 1e-4, \\(\beta_{1} = 0.9\\) and \\(\beta_{2} = 0.999\\), a weight decay of 0.01, learning rate warmup for 10,000 steps and linear decay of the learning rate after. ## Evaluation results - We evaluate our pre-trained language models on five NLP tasks: NER, POS tagging, sentiment analysis, dialect identification, and poetry classification. - We fine-tune and evaluate the models using 12 dataset. - We used Hugging Face's transformers to fine-tune our CAMeLBERT models. - We used transformers `v3.1.0` along with PyTorch `v1.5.1`. - The fine-tuning was done by adding a fully connected linear layer to the last hidden state. - We use \\(F_{1}\\) score as a metric for all tasks. - Code used for fine-tuning is available [here](https://github.com/CAMeL-Lab/CAMeLBERT). ### Results | Task | Dataset | Variant | Mix | CA | DA | MSA | MSA-1/2 | MSA-1/4 | MSA-1/8 | MSA-1/16 | | -------------------- | --------------- | ------- | ----- | ----- | ----- | ----- | ------- | ------- | ------- | -------- | | NER | ANERcorp | MSA | 80.2% | 66.2% | 74.2% | 82.4% | 82.3% | 82.0% | 82.3% | 80.5% | | POS | PATB (MSA) | MSA | 97.3% | 96.6% | 96.5% | 97.4% | 97.4% | 97.4% | 97.4% | 97.4% | | | ARZTB (EGY) | DA | 90.1% | 88.6% | 89.4% | 90.8% | 90.3% | 90.5% | 90.5% | 90.4% | | | Gumar (GLF) | DA | 97.3% | 96.5% | 97.0% | 97.1% | 97.0% | 97.0% | 97.1% | 97.0% | | SA | ASTD | MSA | 76.3% | 69.4% | 74.6% | 76.9% | 76.0% | 76.8% | 76.7% | 75.3% | | | ArSAS | MSA | 92.7% | 89.4% | 91.8% | 93.0% | 92.6% | 92.5% | 92.5% | 92.3% | | | SemEval | MSA | 69.0% | 58.5% | 68.4% | 72.1% | 70.7% | 72.8% | 71.6% | 71.2% | | DID | MADAR-26 | DA | 62.9% | 61.9% | 61.8% | 62.6% | 62.0% | 62.8% | 62.0% | 62.2% | | | MADAR-6 | DA | 92.5% | 91.5% | 92.2% | 91.9% | 91.8% | 92.2% | 92.1% | 92.0% | | | MADAR-Twitter-5 | MSA | 75.7% | 71.4% | 74.2% | 77.6% | 78.5% | 77.3% | 77.7% | 76.2% | | | NADI | DA | 24.7% | 17.3% | 20.1% | 24.9% | 24.6% | 24.6% | 24.9% | 23.8% | | Poetry | APCD | CA | 79.8% | 80.9% | 79.6% | 79.7% | 79.9% | 80.0% | 79.7% | 79.8% | ### Results (Average) | | Variant | Mix | CA | DA | MSA | MSA-1/2 | MSA-1/4 | MSA-1/8 | MSA-1/16 | | -------------------- | ------- | ----- | ----- | ----- | ----- | ------- | ------- | ------- | -------- | | Variant-wise-average[[1]](#footnote-1) | MSA | 81.9% | 75.3% | 79.9% | 83.2% | 82.9% | 83.1% | 83.0% | 82.1% | | | DA | 73.5% | 71.1% | 72.1% | 73.5% | 73.1% | 73.4% | 73.3% | 73.1% | | | CA | 79.8% | 80.9% | 79.6% | 79.7% | 79.9% | 80.0% | 79.7% | 79.8% | | Macro-Average | ALL | 78.2% | 74.0% | 76.6% | 78.9% | 78.6% | 78.8% | 78.7% | 78.2% | [1]: Variant-wise-average refers to average over a group of tasks in the same language variant. ## Acknowledgements This research was supported with Cloud TPUs from Google’s TensorFlow Research Cloud (TFRC). ## Citation ```bibtex @inproceedings{inoue-etal-2021-interplay, title = "The Interplay of Variant, Size, and Task Type in {A}rabic Pre-trained Language Models", author = "Inoue, Go and Alhafni, Bashar and Baimukan, Nurpeiis and Bouamor, Houda and Habash, Nizar", booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop", month = apr, year = "2021", address = "Kyiv, Ukraine (Online)", publisher = "Association for Computational Linguistics", 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.", } ```