UBC-NLP/InfoDCL-BERTweet-hashtag

Contrastive Learning of Sociopragmatic Meaning in Social Media

Chiyu Zhang, Muhammad Abdul-Mageed, Ganesh Jarwaha

Publish at Findings of ACL 2023

Paper

Illustration of our proposed InfoDCL framework. We exploit distant/surrogate labels (i.e., emojis) to supervise two contrastive losses, corpus-aware contrastive loss (CCL) and Light label-aware contrastive loss (LCL-LiT). Sequence representations from our model should keep the cluster of each class distinguishable and preserve semantic relationships between classes.

Checkpoints of Models Pre-Trained with InfoDCL

• 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

Model Performance

Fine-tuning results on our 24 Socio-pragmatic Meaning datasets (average macro-F1 over five runs).