A Unified Generative Framework for Multilingual Euphemism Detection and Identification

Anonymous

Abstract: Currently, various euphemisms are emerging in social networks, attracting widespread attention from the natural language processing community. However, existing euphemism datasets are only domain-specific or language-specific. In addition, existing approaches to the study of euphemisms are one-sided. Either only the euphemism detection task or only the euphemism identification task is accomplished, lacking a unified framework. To this end, we construct a large-scale Multi-lingual Multi-category dataset of Euphemisms named MME, which covers a total of 12 categories for two languages i.e., English and Chinese. Then, we first propose a unified generative model to Jointly conduct the tasks of multilingual Euphemism Detection and Identification named JointEDI. By comparing with LLMs and human evaluation, we demonstrate the effectiveness of the proposed JointEDI and the feasibility of unifying euphemism detection and identification tasks. Moreover, the MME dataset also provides a new reference standard for euphemism detection and identification.

Paper Type: long

Research Area: Semantics: Lexical

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English, Chinese