Skip to content

Official Implementation for Pre-CoFactv2 (AAAI-23 DeFactify2.0 Workshop 1st Place)

Notifications You must be signed in to change notification settings

wwweiwei/Pre-CoFactv2-AAAI-2023

Repository files navigation

Official code of Team Triple-Check at Multi-Modal-Fact-Verification-2023

🎉 🎉 We won the 🔥first place🔥 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.

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.

Metric

F1 averaged across the 5 categories. The final ranking would be based on the weighted average F1 score.

Pre_CoFactv2 Overview

Experiment Overview

Leaderboard

About

Official Implementation for Pre-CoFactv2 (AAAI-23 DeFactify2.0 Workshop 1st Place)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages