Fake News Detection as Natural Language Inference

TL;DR

This paper presents a novel approach to fake news detection by framing it as a natural language inference task, utilizing ensemble models and noisy label training to achieve high accuracy.

Contribution

It introduces a new perspective on fake news detection as NLI and combines multiple models with noisy label retraining for improved performance.

Findings

Achieved 88.063% accuracy in the WSDM 2019 challenge

Ensemble of NLI models outperforms individual models

Identified reliable test cases based on transitivity relations

Abstract

This report describes the entry by the Intelligent Knowledge Management (IKM) Lab in the WSDM 2019 Fake News Classification challenge. We treat the task as natural language inference (NLI). We individually train a number of the strongest NLI models as well as BERT. We ensemble these results and retrain with noisy labels in two stages. We analyze transitivity relations in the train and test sets and determine a set of test cases that can be reliably classified on this basis. The remainder of test cases are classified by our ensemble. Our entry achieves test set accuracy of 88.063% for 3rd place in the competition.