Bertweet Tb2 Ewt Pos Tagging

🚀 Twitter POS Tagging Model

This is a state - of - the - art Twitter POS tagging model with high accuracy, trained on combined data for better performance in social media analysis.

🚀 Quick Start

This model is the state - of - the - art Twitter POS tagging model (with 95.38% Accuracy) on Tweebank V2's NER benchmark (also called Tweebank - NER). It is trained on the corpus that combines both Tweebank - NER and English - EWT training data.

For more details about the TweebankNLP project, please refer to this our paper and [github](https://github.com/social - machines/TweebankNLP) page. In the paper, it is referred to as HuggingFace - BERTweet (TB2+EWT) in the POS table.

💻 Usage Examples

Basic Usage

When using the model, pre - processing is crucial for optimal performance. When you apply the model on tweets, please make sure that tweets are preprocessed by the TweetTokenizer.

from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("TweebankNLP/bertweet-tb2_ewt-pos-tagging")

model = AutoModelForTokenClassification.from_pretrained("TweebankNLP/bertweet-tb2_ewt-pos-tagging")

📄 License

This project is licensed under the cc - by - nc - 4.0 license.

📚 References

If you use this repository in your research, please kindly cite our paper:

@article{jiang2022tweetnlp,
    title={Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis},
    author={Jiang, Hang and Hua, Yining and Beeferman, Doug and Roy, Deb},
    journal={In Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
    year={2022}
}