Task-Oriented Automatic Fact-Checking with Frame-Semantics
This addresses the problem of verifying claims for fact-checkers and researchers, though it appears incremental as it builds on existing semantic frameworks with new datasets.
The paper tackles automatic fact-checking by using frame semantics to better understand claims, showing effectiveness in improving evidence retrieval and explainability through case studies on voting-related and OECD-based claims.
We propose a novel paradigm for automatic fact-checking that leverages frame semantics to enhance the structured understanding of claims and guide the process of fact-checking them. To support this, we introduce a pilot dataset of real-world claims extracted from PolitiFact, specifically annotated for large-scale structured data. This dataset underpins two case studies: the first investigates voting-related claims using the Vote semantic frame, while the second explores various semantic frames based on data sources from the Organisation for Economic Co-operation and Development (OECD). Our findings demonstrate the effectiveness of frame semantics in improving evidence retrieval and explainability for fact-checking. Finally, we conducted a survey of frames evoked in fact-checked claims, identifying high-impact frames to guide future work in this direction.