Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

Enhancing Natural Language Inference Performance with Knowledge Graph for COVID-19 Automated Fact-Checking in Indonesian Language

Created by
  • Haebom

Author

Arief Purnama Muharram, Ayu Purwarianti

Outline

This paper proposes a method for leveraging knowledge graphs (KGs) to improve the performance of an automated fact-checking system for COVID-19 in Indonesian. To overcome the limitations of existing automatic fact-checking systems based on Natural Language Inference (NLI), we present a model architecture comprised of three modules: a fact module, an NLI module, and a classifier module. The fact module processes information from the KG, while the NLI module processes the semantic relationship between given premises and hypotheses. The representation vectors from both modules are concatenated and fed into the classifier module to produce the final result. The model was trained using the Indonesian COVID-19 fact-checking dataset and the COVID-19 KG Bahasa Indonesia, achieving an accuracy of 0.8616, demonstrating the effectiveness of utilizing KGs.

Takeaways, Limitations

•
Takeaways:
◦
We demonstrate that leveraging knowledge graphs (KGs) can improve the accuracy of an Indonesian-language automated fact-checking system for COVID-19.
◦
A novel methodology for improving the performance of natural language inference (NLI)-based automatic fact-checking systems is presented.
◦
Takeaways provided for the development of an automated fact-checking system in a multilingual environment.
•
Limitations:
◦
Lack of detailed description of the dataset used and the size and quality of the KG.
◦
Further verification of the generalization performance of the proposed model is needed.
◦
Further research is needed on applicability to other languages or other topics.
👍
Made with Slashpage