Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic Claims

TL;DR

This paper introduces a new dataset and novel NLI-based methods, including graph convolutional networks and attention mechanisms, for automated COVID-19 misinformation verification, demonstrating competitive results against state-of-the-art approaches.

Contribution

The work presents a novel COVID-19 claim dataset and innovative NLI-based techniques for veracity assessment, advancing automated misinformation detection.

Findings

Proposed methods are competitive with SOTA techniques.

Constructed the PANACEA dataset with heterogeneous COVID-19 claims.

Demonstrated effectiveness of graph convolutional and attention-based models.

Abstract

We present a comprehensive work on automated veracity assessment from dataset creation to developing novel methods based on Natural Language Inference (NLI), focusing on misinformation related to the COVID-19 pandemic. We first describe the construction of the novel PANACEA dataset consisting of heterogeneous claims on COVID-19 and their respective information sources. The dataset construction includes work on retrieval techniques and similarity measurements to ensure a unique set of claims. We then propose novel techniques for automated veracity assessment based on Natural Language Inference including graph convolutional networks and attention based approaches. We have carried out experiments on evidence retrieval and veracity assessment on the dataset using the proposed techniques and found them competitive with SOTA methods, and provided a detailed discussion.