Euphemistic Phrase Detection by Masked Language Model

TL;DR

This paper introduces a novel method for automatically detecting multi-word euphemistic phrases in social media texts by combining phrase mining, word embeddings, and masked language models, significantly improving detection accuracy.

Contribution

It is the first work to automatically detect multi-word euphemisms using a combination of phrase mining, embeddings, and SpanBERT, advancing NLP capabilities in social media moderation.

Findings

20-50% higher detection accuracy than baselines

Effective detection of multi-word euphemisms in social media

Combines phrase mining, embeddings, and masked language models

Abstract

It is a well-known approach for fringe groups and organizations to use euphemisms -- ordinary-sounding and innocent-looking words with a secret meaning -- to conceal what they are discussing. For instance, drug dealers often use "pot" for marijuana and "avocado" for heroin. From a social media content moderation perspective, though recent advances in NLP have enabled the automatic detection of such single-word euphemisms, no existing work is capable of automatically detecting multi-word euphemisms, such as "blue dream" (marijuana) and "black tar" (heroin). Our paper tackles the problem of euphemistic phrase detection without human effort for the first time, as far as we are aware. We first perform phrase mining on a raw text corpus (e.g., social media posts) to extract quality phrases. Then, we utilize word embedding similarities to select a set of euphemistic phrase candidates. Finally, we rank those candidates by a masked language model -- SpanBERT. Compared to strong baselines, we report 20-50% higher detection accuracies using our algorithm for detecting euphemistic phrases.