cardiffnlp/twitter-roberta-base-tempo-wic-latest

This is a RoBERTa-base model trained on 154M tweets until the end of December 2022 and finetuned for meaning shift detection (binary classification) on the TempoWIC 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_1 = "'In this bullpen, you should be able to ask why and understand why we do the things we do.' @Trisha_Ford 😍 #pitchstock2020 @user"
text_2 = "Castro needs to be the last bullpen guy to pitch."
target = "bullpen"
text_input = f"{text_1}</s>{text_2}</s>{target}"

pipe = pipeline('text-classification', model="cardiffnlp/twitter-roberta-base-tempo-wic-latest")
pipe(text_input)
>> [{'label': 'yes', 'score': 0.9964596629142761}]

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}
}