# Uni-DUE Student Team: Tackling fact checking through decomposable attention neural network

## TL;DR

This paper introduces a fact-checking system that combines search and neural network filtering to verify claims using Wikipedia, achieving significant improvements in accuracy on the FEVER dataset.

## Contribution

The authors develop a decomposable attention neural network for fact verification, enhancing the FEVER challenge performance by 25.5% over the baseline.

## Key findings

- Achieved FEVER score of 0.3927 on development data.
- System effectively filters noise and supports claim verification.
- Significant improvement over baseline performance.

## Abstract

In this paper we present our system for the FEVER Challenge. The task of this challenge is to verify claims by extracting information from Wikipedia. Our system has two parts. In the first part it performs a search for candidate sentences by treating the claims as query. In the second part it filters out noise from these candidates and uses the remaining ones to decide whether they support or refute or entail not enough information to verify the claim. We show that this system achieves a FEVER score of 0.3927 on the FEVER shared task development data set which is a 25.5% improvement over the baseline score.