Skip to content

An automated fact-checking system that uses named entity recognition, TF-IDF vector comparison and decomposable attention models.

Notifications You must be signed in to change notification settings

wxj1818/DeFactoNLP

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

83 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DeFactoNLP

DeFactoNLP is an automated fact-checking system designed for the FEVER 2018 Shared Task which was held at EMNLP 2018. It is capable of verifying claims and retrieving sentences from Wikipedia which support the assessment. This is accomplished through the usage of named entity recognition, TF-IDF vector comparison and decomposable attention models.

If you use this code, please cite:

@inproceedings{Reddy2018, 
title={DeFactoNLP: Fact Verification using Entity Recognition, TFIDF Vector Comparison and Decomposable Attention}, 
publisher={FEVER 2018, organised under EMNLP 2018}, 
author={Reddy, Aniketh Janardhan and Rocha, Gil and Esteves, Diego},
year={2018}
}

About

An automated fact-checking system that uses named entity recognition, TF-IDF vector comparison and decomposable attention models.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.0%
  • Shell 1.4%
  • Java 1.4%
  • Other 0.2%