cardiffnlp/twitter-roberta-base-nerd-latest

This is a RoBERTa-base model trained on 154M tweets until the end of December 2022 and finetuned for name entity Disambiguation (binary classification) on the TweetNERD dataset of SuperTweetEval. The original Twitter-based RoBERTa model can be found here.

Labels

"id2label": { "0": "no", "1": "yes" }

Example

from transformers import pipeline
text = 'Banana+Nutella snack pack=someone is gonna see me crying in the break room'
definition = 'chocolate hazelnut spread manufactured by Ferrero'
target = 'Nutella'

model = "cardiffnlp/twitter-roberta-base-nerd-latest"
tokenizer = "cardiffnlp/twitter-roberta-base-nerd-latest"

text_input = f"{text} </s> {definition} </s> {target}"
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
pipe(text_input)
>> [{'label': 'yes', 'score': 0.9993378520011902}]

Citation Information

Please cite the reference paper if you use this model.

@inproceedings{antypas2023supertweeteval,
  title={SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research},
  author={Dimosthenis Antypas and Asahi Ushio and Francesco Barbieri and Leonardo Neves and Kiamehr Rezaee and Luis Espinosa-Anke and Jiaxin Pei and Jose Camacho-Collados},
  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2023},
  year={2023}
}