Proceedings

Multi-Hop Fact Checking of Political Claims

Wojciech Ostrowski, Arnav Arora, Pepa Atanasova, Isabelle Augenstein

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3892-3898.

https://doi.org/10.24963/ijcai.2021/536

Keywords

  • Natural Language Processing: Text Classification
  • Natural Language Processing: Resources and Evaluation
  • Natural Language Processing: NLP Applications and Tools

Abstract

Recent work has proposed multi-hop models and datasets for studying complex natural language reasoning. One notable task requiring multi-hop reasoning is fact checking, where a set of connected evidence pieces leads to the final verdict of a claim. However, existing datasets either do not provide annotations for gold evidence pages, or the only dataset which does (FEVER) mostly consists of claims which can be fact-checked with simple reasoning and is constructed artificially. Here, we study more complex claim verification of naturally occurring claims with multiple hops over interconnected evidence chunks. We: 1) construct a small annotated dataset, PolitiHop, of evidence sentences for claim verification; 2) compare it to existing multi-hop datasets; and 3) study how to transfer knowledge from more extensive in- and out-of-domain resources to PolitiHop. We find that the task is complex and achieve the best performance with an architecture that specifically models reasoning over evidence pieces in combination with in-domain transfer learning.

Wojciech Ostrowski, Arnav Arora, Pepa Atanasova, and Isabelle Augenstein. 2021. Multi-Hop Fact Checking of Political Claims. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3892–3898. https://doi.org/10.24963/ijcai.2021/536
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards