Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims
This work addresses the challenge of identifying claims that need fact-checking, which is incremental as it builds on existing transformer methods with adversarial training.
The paper tackles the problem of detecting check-worthy factual claims by introducing an adversarially-regularized transformer model, achieving a 4.70 point F1-score improvement over state-of-the-art models on the ClaimBuster and CLEF2019 datasets.
We present a study on the efficacy of adversarial training on transformer neural network models, with respect to the task of detecting check-worthy claims. In this work, we introduce the first adversarially-regularized, transformer-based claim spotter model that achieves state-of-the-art results on multiple challenging benchmarks. We obtain a 4.70 point F1-score improvement over current state-of-the-art models on the ClaimBuster Dataset and CLEF2019 Dataset, respectively. In the process, we propose a method to apply adversarial training to transformer models, which has the potential to be generalized to many similar text classification tasks. Along with our results, we are releasing our codebase and manually labeled datasets. We also showcase our models' real world usage via a live public API.