Low-Resource Clickbait Spoiling for Indonesian via Question Answering
Document Type
Conference Proceeding
Publication Title
2023 10th International Conference on Advanced Informatics: Concept, Theory and Application, ICAICTA 2023
Abstract
Clickbait spoiling aims to generate a short text to satisfy the curiosity induced by a clickbait post. As it is a newly introduced task, the dataset is only available in English so far. Our contributions include the construction of manually labeled clickbait spoiling corpus in Indonesian and an evaluation on using cross-lingual zero-shot question answering-based models to tackle clikcbait spoiling for low-resource language like In-donesian. We utilize selection of multilingual language models. The experimental results suggest that XLM-RoBERTa (large) model outperforms other models for phrase and passage spoilers, meanwhile, mDeBERTa (base) model outperforms other models for multipart spoilers.
DOI
10.1109/ICAICTA59291.2023.10389952
Publication Date
1-1-2023
Keywords
clickbait, clickbait spoiling, cross-lingual, low-resource language, question answering, zero-shot
Recommended Citation
N. Intan Maharani et al., "Low-Resource Clickbait Spoiling for Indonesian via Question Answering," 2023 10th International Conference on Advanced Informatics: Concept, Theory and Application, ICAICTA 2023, Jan 2023.
The definitive version is available at https://doi.org/10.1109/ICAICTA59291.2023.10389952