HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation
This addresses check-worthiness estimation for fact-checking systems, but it is incremental as it builds on existing language models with structured data enhancements.
The paper tackled check-worthiness estimation by enriching language models like RoBERTa with structured triple embeddings from text, resulting in improved performance, with a best F1 score of 71.1 in English ranking 12th out of 27 candidates.
This paper summarizes the experiments and results of the HYBRINFOX team for the CheckThat! 2024 - Task 1 competition. We propose an approach enriching Language Models such as RoBERTa with embeddings produced by triples (subject ; predicate ; object) extracted from the text sentences. Our analysis of the developmental data shows that this method improves the performance of Language Models alone. On the evaluation data, its best performance was in English, where it achieved an F1 score of 71.1 and ranked 12th out of 27 candidates. On the other languages (Dutch and Arabic), it obtained more mixed results. Future research tracks are identified toward adapting this processing pipeline to more recent Large Language Models.