Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings

TL;DR

This paper investigates euphemism detection in few-shot and zero-shot scenarios using RoBERTa and GPT-3, showing models can classify unseen euphemisms effectively, highlighting their understanding of higher-level euphemistic concepts.

Contribution

It extends the euphemism detection task to few-shot and zero-shot settings and evaluates large language models' ability to generalize to unseen euphemisms.

Findings

Language models classify unseen euphemisms well

Models capture higher-level euphemistic concepts

Effective in few-shot and zero-shot settings

Abstract

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.