Generating Fact Checking Explanations

04/13/2020
by   Pepa Atanasova, et al.
12

Most existing work on automated fact checking is concerned with predicting the veracity of claims based on metadata, social network spread, language used in claims, and, more recently, evidence supporting or denying claims. A crucial piece of the puzzle that is still missing is to understand how to automate the most elaborate part of the process – generating justifications for verdicts on claims. This paper provides the first study of how these explanations can be generated automatically based on available claim context, and how this task can be modelled jointly with veracity prediction. Our results indicate that optimising both objectives at the same time, rather than training them separately, improves the performance of a fact checking system. The results of a manual evaluation further suggest that the informativeness, coverage and overall quality of the generated explanations are also improved in the multi-task model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/19/2020

Explainable Automated Fact-Checking for Public Health Claims

Fact-checking is the task of verifying the veracity of claims by assessi...
research
06/21/2019

Explainable Fact Checking with Probabilistic Answer Set Programming

One challenge in fact checking is the ability to improve the transparenc...
research
09/15/2020

Social network analytics for supervised fraud detection in insurance

Insurance fraud occurs when policyholders file claims that are exaggerat...
research
07/30/2021

Automatic Claim Review for Climate Science via Explanation Generation

There is unison is the scientific community about human induced climate ...
research
04/07/2023

Interpretable Unified Language Checking

Despite recent concerns about undesirable behaviors generated by large l...
research
03/24/2022

Generating Scientific Claims for Zero-Shot Scientific Fact Checking

Automated scientific fact checking is difficult due to the complexity of...
research
06/02/2021

Evidence-based Factual Error Correction

This paper introduces the task of factual error correction: performing e...

Please sign up or login with your details

Forgot password? Click here to reset