Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims

TL;DR

This paper introduces MTM, a memory-enhanced transformer model that improves detection of previously fact-checked claims by leveraging key sentences with event and pattern information, outperforming existing methods.

Contribution

The paper proposes a novel reranker that combines event and pattern information through memory-enhanced transformers to better identify relevant fact-checking articles.

Findings

MTM outperforms existing reranking methods on real-world datasets.

Human evaluation shows MTM effectively captures key sentences for explanations.

The model leverages ROUGE-guided fine-tuning and pattern vectors for improved matching.

Abstract

False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works focus on providing evidence for detection by reranking candidate fact-checking articles (FC-articles) retrieved by BM25. However, these performances may be limited because they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics; (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. Models that ignore the two aspects only leverage semantic relevance and may be misled by sentences that describe similar but irrelevant events. In this paper, we propose a novel reranker, MTM (Memory-enhanced Transformers for Matching) to rank FC-articles using key sentences selected with event (lexical and semantic) and pattern information. For event information, we propose a ROUGE-guided Transformer which is finetuned with regression of ROUGE. For pattern information, we generate pattern vectors for matching with sentences. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations. The code and the dataset are at https://github.com/ICTMCG/MTM.