Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings
This addresses euphemism detection for NLP applications, but it is incremental as it extends an existing shared task to new settings.
The paper tackled euphemism detection in few-shot and zero-shot settings using RoBERTa and GPT-3 on a shared task dataset, finding that language models classify euphemistic terms relatively well even on unseen terms, indicating they capture higher-level concepts.
This work builds upon the Euphemism Detection Shared Task proposed in the EMNLP 2022 FigLang Workshop, and extends it to few-shot and zero-shot settings. We demonstrate a few-shot and zero-shot formulation using the dataset from the shared task, and we conduct experiments in these settings using RoBERTa and GPT-3. Our results show that language models are able to classify euphemistic terms relatively well even on new terms unseen during training, indicating that it is able to capture higher-level concepts related to euphemisms.