MarsEclipse at SemEval-2023 Task 3: Multi-Lingual and Multi-Label Framing Detection with Contrastive Learning
This addresses framing detection in multiple languages for NLP researchers, but it is incremental as it builds on existing contrastive learning and pre-trained models.
The paper tackled multi-lingual and multi-label framing detection by fine-tuning pre-trained language models with a multi-label contrastive loss, achieving first place on the official test set and leaderboard for five out of six languages.
This paper describes our system for SemEval-2023 Task 3 Subtask 2 on Framing Detection. We used a multi-label contrastive loss for fine-tuning large pre-trained language models in a multi-lingual setting, achieving very competitive results: our system was ranked first on the official test set and on the official shared task leaderboard for five of the six languages for which we had training data and for which we could perform fine-tuning. Here, we describe our experimental setup, as well as various ablation studies. The code of our system is available at https://github.com/QishengL/SemEval2023