# MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms

arXiv: https://arxiv.org/abs/2401.14526 · HTML: https://mlsanity.com/paper/2401.14526/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 8 of 8)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Self-Supervised Euphemism Detection and Identification for Content Moderation](https://mlsanity.com/paper/2103.16808/) (2021)
- [CATs are Fuzzy PETs: A Corpus and Analysis of Potentially Euphemistic Terms](https://mlsanity.com/paper/2205.02728/) (2022)
- [NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification](https://mlsanity.com/paper/2305.10971/) (2023)
- [Searching for PETs: Using Distributional and Sentiment-Based Methods to Find Potentially Euphemistic Terms](https://mlsanity.com/paper/2205.10451/) (2022)
- [A Report on the Euphemisms Detection Shared Task](https://mlsanity.com/paper/2211.13327/) (2022)
- [Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings](https://mlsanity.com/paper/2210.12926/) (2022)
- [FEED PETs: Further Experimentation and Expansion on the Disambiguation of Potentially Euphemistic Terms](https://mlsanity.com/paper/2306.00217/) (2023)

## Built on by (most cited first, 3 of 3)

- [Turkish Delights: a Dataset on Turkish Euphemisms](https://mlsanity.com/paper/2407.13040/) (2024)
- [When Does Language Transfer Help? Sequential Fine-Tuning for Cross-Lingual Euphemism Detection](https://mlsanity.com/paper/2508.11831/) (2025)
- [When Semantic Overlap Is Not Enough: Cross-Lingual Euphemism Transfer Between Turkish and English](https://mlsanity.com/paper/2602.16957/) (2026)

## Abstract (arXiv)

This study investigates the computational processing of euphemisms, a universal linguistic phenomenon, across multiple languages. We train a multilingual transformer model (XLM-RoBERTa) to disambiguate potentially euphemistic terms (PETs) in multilingual and cross-lingual settings. In line with current trends, we demonstrate that zero-shot learning across languages takes place. We also show cases where multilingual models perform better on the task compared to monolingual models by a statistically significant margin, indicating that multilingual data presents additional opportunities for models to learn about cross-lingual, computational properties of euphemisms. In a follow-up analysis, we focus on universal euphemistic "categories" such as death and bodily functions among others. We test to see whether cross-lingual data of the same domain is more important than within-language data of other domains to further understand the nature of the cross-lingual transfer.