Claim Verification using a Multi-GAN based Model
arXiv:2103.08001
Abstract
This article describes research on claim verification carried out using a multiple GAN-based model. The proposed model consists of three pairs of generators and discriminators. The generator and discriminator pairs are responsible for generating synthetic data for supported and refuted claims and claim labels. A theoretical discussion about the proposed model is provided to validate the equilibrium state of the model. The proposed model is applied to the FEVER dataset, and a pre-trained language model is used for the input text data. The synthetically generated data helps to gain information which helps the model to perform better than state of the art models and other standard classifiers.
arXiv commentPaper is submitted at LDK 2021 3rd Conference on Language, Data and Knowledge
References in corpus (7)
- Scikit-learn: Machine Learning in Python
- Automatic Detection of Fake News
- TI-CNN: Convolutional Neural Networks for Fake News Detection
- Long Text Generation via Adversarial Training with Leaked Information
- DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning
- Adversarial Text Generation Without Reinforcement Learning
- Adversarial attacks against Fact Extraction and VERification