---
title: "Multi-Hop Fact Checking of Political Claims"
authors:
  - "Wojciech Ostrowski"
  - "Arnav Arora"
  - "Pepa Atanasova"
  - "Isabelle Augenstein"
doi: "10.24963/ijcai.2021/536"
url: "https://ijcai.org/proceedings/2021/536"
pdf: "https://ijcai.org/proceedings/2021/0536.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "3892-3898"
track: "Main Track"
keywords:
  - "Natural Language Processing: Text Classification"
  - "Natural Language Processing: Resources and Evaluation"
  - "Natural Language Processing: NLP Applications and Tools"
---

# Multi-Hop Fact Checking of Political Claims

Wojciech Ostrowski, Arnav Arora, Pepa Atanasova, Isabelle Augenstein

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 3892-3898. DOI: [10.24963/ijcai.2021/536](https://doi.org/10.24963/ijcai.2021/536)

## 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.