FarFetched: Entity-centric Reasoning and Claim Validation for the Greek Language based on Textually Represented Environments

TL;DR

FarFetched is an entity-centric reasoning framework that automates claim validation in Greek by integrating evidence from multiple sources, using graph-based reasoning, semantic similarity, and textual entailment to assess credibility.

Contribution

It introduces a novel approach for claim validation in Greek, combining entity linking, graph reasoning, and textual entailment, addressing resource scarcity in less-resourced languages.

Findings

Effective entity linking and graph reasoning for Greek.

Semantic similarity models trained on translated benchmarks.

Successful claim validation demonstration in Greek.

Abstract

Our collective attention span is shortened by the flood of online information. With \textit{FarFetched}, we address the need for automated claim validation based on the aggregated evidence derived from multiple online news sources. We introduce an entity-centric reasoning framework in which latent connections between events, actions, or statements are revealed via entity mentions and represented in a graph database. Using entity linking and semantic similarity, we offer a way for collecting and combining information from diverse sources in order to generate evidence relevant to the user's claim. Then, we leverage textual entailment recognition to quantitatively determine whether this assertion is credible, based on the created evidence. Our approach tries to fill the gap in automated claim validation for less-resourced languages and is showcased on the Greek language, complemented by the training of relevant semantic textual similarity (STS) and natural language inference (NLI) models that are evaluated on translated versions of common benchmarks.