Distilling the Evidence to Augment Fact Verification Models

Beatrice Portelli, Jason Zhao, Tal Schuster, Giuseppe Serra, Enrico Santus


Abstract
The alarming spread of fake news in social media, together with the impossibility of scaling manual fact verification, motivated the development of natural language processing techniques to automatically verify the veracity of claims. Most approaches perform a claim-evidence classification without providing any insights about why the claim is trustworthy or not. We propose, instead, a model-agnostic framework that consists of two modules: (1) a span extractor, which identifies the crucial information connecting claim and evidence; and (2) a classifier that combines claim, evidence, and the extracted spans to predict the veracity of the claim. We show that the spans are informative for the classifier, improving performance and robustness. Tested on several state-of-the-art models over the Fever dataset, the enhanced classifiers consistently achieve higher accuracy while also showing reduced sensitivity to artifacts in the claims.
Anthology ID:
2020.fever-1.7
Volume:
Proceedings of the Third Workshop on Fact Extraction and VERification (FEVER)
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | FEVER | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
47–51
Language:
URL:
https://www.aclweb.org/anthology/2020.fever-1.7
DOI:
10.18653/v1/2020.fever-1.7
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.fever-1.7.pdf
Video:
 http://slideslive.com/38929665