Skip to content

darachubarova/SNA-25

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 

Repository files navigation

SNA-25

Authors

Daria Chubarova, Ivan Efimenkov

Abstract

In law, finance, and journalism, identifying contradictions in texts is important to ensure data integrity. Traditional methods are often ineffective. The article presents a contradiction detection system using knowledge graphs (KG). The system includes data processing, KG construction, embedding training, classification models, and evaluation. Methodology: text transformation into knowledge triples, KG compliance (DBpedia, Wikidata, UML), application of reasoning algorithms. Experiments on FEVER show a high accuracy of detecting contradictions with the KG model. The system is an effective tool for analyzing text data. Prospects: improving models, adapting to other languages and domains

Description

Results folder include metrics from the last execution (5 epoch)

code_gpu_10.py provides approach with 5 epochs

code_gpu_11.py - 2 epochs

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages