Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News
Computation and Language
2021-04-28 v1
Abstract
In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank -- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise.
Keywords
Cite
@article{arxiv.2104.12918,
title = {Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News},
author = {Ashkan Kazemi and Zehua Li and Verónica Pérez-Rosas and Rada Mihalcea},
journal= {arXiv preprint arXiv:2104.12918},
year = {2021}
}
Comments
Accepted to NLP for Internet Freedom Workshop at NAACL 2021