DeepAI AI Chat
Log In Sign Up

Automatic Fact-guided Sentence Modification

09/30/2019
by   Darsh J Shah, et al.
MIT
0

Online encyclopediae like Wikipedia contain large amounts of text that need frequent corrections and updates. The new information may contradict existing content in encyclopediae. In this paper, we focus on rewriting such dynamically changing articles. This is a challenging constrained generation task, as the output must be consistent with the new information and fit into the rest of the existing document. To this end, we propose a two-step solution: (1) We identify and remove the contradicting components in a target text for a given claim, using a neutralizing stance model; (2) We expand the remaining text to be consistent with the given claim, using a novel two-encoder sequence-to-sequence model with copy attention. Applied to a Wikipedia fact update dataset, our method successfully generates updated sentences for new claims, achieving the highest SARI score. Furthermore, we demonstrate that generating synthetic data through such rewritten sentences can successfully augment the FEVER fact-checking training dataset, leading to a relative error reduction of 13

READ FULL TEXT

page 1

page 2

page 3

page 4

04/16/2021

WhatTheWikiFact: Fact-Checking Claims Against Wikipedia

The rise of Internet has made it a major source of information. Unfortun...
11/16/2021

WikiContradiction: Detecting Self-Contradiction Articles on Wikipedia

While Wikipedia has been utilized for fact-checking and claim verificati...
12/27/2018

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

In this paper we present our system for the FEVER Challenge. The task of...
02/03/2021

Self-Supervised Claim Identification for Automated Fact Checking

We propose a novel, attention-based self-supervised approach to identify...
10/06/2020

Fact Extraction and VERification – The FEVER case: An Overview

Fact Extraction and VERification (FEVER) is a recently introduced task w...
02/21/2017

Learning to generate one-sentence biographies from Wikidata

We investigate the generation of one-sentence Wikipedia biographies from...