InfoDCL-Emoji-XLMR-Base

The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages

<p align="center"> <a href="https://chiyuzhang94.github.io/" target="_blank">Chiyu Zhang</a>, Khai Duy Doan, Qisheng Liao, <a href="https://mageed.arts.ubc.ca/" target="_blank">Muhammad Abdul-Mageed</a></p> <p align="center" float="left"> <p align="center" float="left"> The University of British Columbia, Mohamed bin Zayed University of Artificial Intelligence </p> <p align="center">Publish at Main Conference of EMNLP 2023</p> <p align="center"> <a href="https://arxiv.org/abs/2310.14557" target="_blank">Paper</a></p>

Checkpoints of Models Pre-Trained with InfoDCL

We further pretrained XLMR/RoBERTa with InfoDCL framework by (Zhang et al. 2023)

Multilingual Model:

• InfoDCL-XLMR trained with multilingual TweetEmoji-multi: https://huggingface.co/UBC-NLP/InfoDCL-Emoji-XLMR-Base

English Models:

• InfoDCL-RoBERTa trained with TweetEmoji-EN: https://huggingface.co/UBC-NLP/InfoDCL-emoji
• InfoDCL-RoBERTa trained with TweetHashtag-EN: https://huggingface.co/UBC-NLP/InfoDCL-hashtag

Citation

Please cite us if you find our data or models useful.

@inproceedings{zhang-etal-2023-skipped,
    title = "The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages",
    author = "Zhang, Chiyu  and
      Khai Duy Doan and,
      Qisheng Liao and,
      Abdul-Mageed, Muhammad",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    year = "2023",
    publisher = "Association for Computational Linguistics",
}