Gigabert V4 Arabic And English

🚀 GigaBERT-v4

GigaBERT-v4 is a model that undergoes continued pre - training of GigaBERT-v3 on code - switched data. It demonstrates enhanced zero - shot transfer performance from English to Arabic in information extraction (IE) tasks. For more details, please refer to the following paper:

@inproceedings{lan2020gigabert,
  author     = {Lan, Wuwei and Chen, Yang and Xu, Wei and Ritter, Alan},
  title      = {GigaBERT: Zero-shot Transfer Learning from English to Arabic},
  booktitle  = {Proceedings of The 2020 Conference on Empirical Methods on Natural Language Processing (EMNLP)},
  year       = {2020}
} 

🚀 Quick Start

📦 Installation

from transformers import *
tokenizer = BertTokenizer.from_pretrained("lanwuwei/GigaBERT-v4-Arabic-and-English", do_lower_case=True)
model = BertForTokenClassification.from_pretrained("lanwuwei/GigaBERT-v4-Arabic-and-English")

💻 Usage Examples

Here is a basic usage example for downloading the model. The downloadable link is GigaBERT-v4.

from transformers import *
tokenizer = BertTokenizer.from_pretrained("lanwuwei/GigaBERT-v4-Arabic-and-English", do_lower_case=True)
model = BertForTokenClassification.from_pretrained("lanwuwei/GigaBERT-v4-Arabic-and-English")