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.
@article{arxiv.2210.12926,
title = {Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings},
author = {Sedrick Scott Keh},
journal= {arXiv preprint arXiv:2210.12926},
year = {2022}
}
Comments
Accepted to EMNLP 2022 Figurative Language Workshop (Euphemism Detection Shared Task). Official code at https://github.com/sedrickkeh/zero-shot-euphemism-detection