Time-Aware Evidence Ranking for Fact-Checking
arXiv:2009.06402 · doi:10.1016/j.websem.2021.100663
Abstract
Truth can vary over time. Fact-checking decisions on claim veracity should therefore take into account temporal information of both the claim and supporting or refuting evidence. In this work, we investigate the hypothesis that the timestamp of a Web page is crucial to how it should be ranked for a given claim. We delineate four temporal ranking methods that constrain evidence ranking differently and simulate hypothesis-specific evidence rankings given the evidence timestamps as gold standard. Evidence ranking in three fact-checking models is ultimately optimized using a learning-to-rank loss function. Our study reveals that time-aware evidence ranking not only surpasses relevance assumptions based purely on semantic similarity or position in a search results list, but also improves veracity predictions of time-sensitive claims in particular.
arXiv comment16 pages, accepted for publication in Journal of Web Semantics - Special Issue on Content Credibility
References in corpus (6)
- Natural Language Inference by Tree-Based Convolution and Heuristic Matching
- Combining Fact Extraction and Verification with Neural Semantic Matching Networks
- Context-Aware Learning to Rank with Self-Attention
- Reasoning Over Semantic-Level Graph for Fact Checking
- Modeling Temporal Evidence from External Collections
- A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction