Claim Verification Using a Multi-GAN Based Model

Amartya Hatua, Arjun Mukherjee, Rakesh Verma


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 that improves classification performance over state of the art baselines. The respective F1 scores after applying the proposed method on FEVER 1.0 and FEVER 2.0 datasets are 0.65+-0.018 and 0.65+-0.051.
Anthology ID:
2021.ranlp-1.56
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
494–503
Language:
URL:
https://aclanthology.org/2021.ranlp-1.56
DOI:
Bibkey:
Cite (ACL):
Amartya Hatua, Arjun Mukherjee, and Rakesh Verma. 2021. Claim Verification Using a Multi-GAN Based Model. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 494–503, Held Online. INCOMA Ltd..
Cite (Informal):
Claim Verification Using a Multi-GAN Based Model (Hatua et al., RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-1.56.pdf
Data
FEVER