Multi-Hop Fact Checking of Political Claims
This addresses the need for more realistic and challenging fact-checking datasets for political claims, though it is incremental as it builds on existing multi-hop reasoning work.
The paper tackles the problem of fact-checking complex political claims requiring multi-hop reasoning by constructing a new dataset, PolitiHop, and finds that an architecture modeling reasoning over evidence with in-domain transfer learning achieves the best performance.
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.