Sabrina Spellman at SemEval-2023 Task 5: Discover the Shocking Truth Behind this Composite Approach to Clickbait Spoiling!
Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/Gutachten › Beitrag in Konferenzband › Beigetragen › Begutachtung
Beitragende
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%.
Details
Originalsprache | Englisch |
---|---|
Titel | Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023) |
Redakteure/-innen | Atul Kr. Ojha, A. Seza Dogruoz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori |
Herausgeber (Verlag) | Association for Computational Linguistics (ACL) |
Seiten | 969-977 |
Seitenumfang | 9 |
ISBN (elektronisch) | 9781959429999 |
Publikationsstatus | Veröffentlicht - 2023 |
Peer-Review-Status | Ja |
Konferenz
Titel | 17th International Workshop on Semantic Evaluation, SemEval 2023, co-located with the 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 |
---|---|
Dauer | 13 - 14 Juli 2023 |
Stadt | Hybrid, Toronto |
Land | Kanada |