Sabrina Spellman at SemEval-2023 Task 5: Discover the Shocking Truth Behind this Composite Approach to Clickbait Spoiling!

Abstract

This paper describes an approach to automatically close the knowledge gap of Clickbait-Posts via a transformer model trained for Question-Answering, augmented by a task-specific post-processing step. This was part of the SemEval 2023 Clickbait shared task (Fröbe et al., 2023a) - specifically task 5. We devised strategies to improve the existing model to fit the task better, e.g. with different special models and a post-processor tailored to different inherent challenges of the task. Furthermore, we explored the possibility of expanding the original training data by using strategies from Heuristic Labeling and Semi-Supervised Learning. With those adjustments, we were able to improve the baseline by 9.8 percentage points to a BLEU-4 score of 48.0%.