Awesome
Official code of Team Triple-Check at Multi-Modal-Fact-Verification-2023
:tada: :tada: We won the :fire:first place:fire: in De-Factify workshop in AAAI-23 and please the technical report can be viewed here. The brief introduction of this work can be referred to our blog.
- Previous verion of our model: Pre_CoFactv1
Task
A multimodality clssification task, where the goal is to detect support, insufficient-evidence and refute between given claims and documents.
Usage
- Train model
bash single_model.sh
- Evaluate model
python evaluate.py ${model_path}
- Ensemble models
python ensemble.py
Dataset
- Train set: 35,000, 7,000 for each class.
- Validation set: 7,500, 1,500 for each class.
- Test set: 7,500, 1,500 for each class.
- For more details, please refer to FACTIFY: A Multi-Modal Fact Verification Dataset.
Metric
F1 averaged across the 5 categories. The final ranking would be based on the weighted average F1 score.