You can deploy this model and start earning money today!

TweebankNLP/
bertweet-tb2-ner

Name: bertweet-tb2-ner
Availability: InStock

Views

No views yet

Model Specification

This is one baseline Twitter NER model (with 73.71% Entity-Level F1) on Tweebank V2's NER benchmark (also called Tweebank-NER), trained on the Tweebank-NER training data.
If you are looking for the SOTA Twitter NER model, please go to this HuggingFace hub link.
For more details about the TweebankNLP project, please refer to this our paper and github page.
In the paper, it is referred as HuggingFace-BERTweet (TB2) in the NER table.

How to use the model

PRE-PROCESSING: when you apply the model on tweets, please make sure that tweets are preprocessed by the TweetTokenizer to get the best performance.

python

from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("TweebankNLP/bertweet-tb2-ner")

model = AutoModelForTokenClassification.from_pretrained("TweebankNLP/bertweet-tb2-ner")

References

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

bibtex

@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}
}