IAI Group at CheckThat! 2024: Transformer Models and Data Augmentation for Checkworthy Claim Detection

TL;DR

This paper details the IAI group's approach using transformer models and data augmentation techniques for multilingual check-worthy claim detection in political debates and social media, achieving top leaderboard placements.

Contribution

It introduces the application of various transformer-based models with data augmentation and transfer learning for multilingual claim detection in a competitive setting.

Findings

Top placements in leaderboard for Arabic and Dutch

Performance drop on unlabeled test data

Insights into language-specific challenges in claim detection

Abstract

This paper describes IAI group's participation for automated check-worthiness estimation for claims, within the framework of the 2024 CheckThat! Lab "Task 1: Check-Worthiness Estimation". The task involves the automated detection of check-worthy claims in English, Dutch, and Arabic political debates and Twitter data. We utilized various pre-trained generative decoder and encoder transformer models, employing methods such as few-shot chain-of-thought reasoning, fine-tuning, data augmentation, and transfer learning from one language to another. Despite variable success in terms of performance, our models achieved notable placements on the organizer's leaderboard: ninth-best in English, third-best in Dutch, and the top placement in Arabic, utilizing multilingual datasets for enhancing the generalizability of check-worthiness detection. Despite a significant drop in performance on the unlabeled test dataset compared to the development test dataset, our findings contribute to the ongoing efforts in claim detection research, highlighting the challenges and potential of language-specific adaptations in claim verification systems.