MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms

Challenge:	Euphemisms are a linguistic device used to soften or neutralize language that may otherwise be harsh or awkward to state directly.
Approach:	They train a multilingual transformer model to disambiguate potentially euphemistic terms in multilingual and cross-lingual settings.
Outcome:	The proposed model performs better than monolingual models on the disambiguation task compared to monolingual ones in multilingual and cross-lingual settings.

Similar Papers

Overview

Challenge

Approach

Outcome

CATs are Fuzzy PETs: A Corpus and Analysis of Potentially Euphemistic Terms (2022.lrec-1)

Copied to clipboard

Martha Gavidia, Patrick Lee, Anna Feldman, JIng Peng

Sentiment Analysis

Challenge:	Euphemisms are a difficult topic because they are subject to language change and humans may not agree on what is a euphemist.
Approach:	They analyze a corpus of potentially euphemistic terms (PETs) and examples from the GloWbE corpus to examine their meanings.
Outcome:	The proposed corpus of potentially euphemistic terms and examples from the GloWbE corpus show that PETs generally decrease negative and offensive sentiment.

Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Senses (2025.findings-naacl)

Copied to clipboard

Samuel Cahyawijaya, Ruochen Zhang, Jan Christian Blaise Cruz, Holy Lovenia, Elisa Gilbert, Hiroki Nomoto, Alham Fikri Aji

Semantic Text Processing

Challenge:	Existing studies on multilingual large language models have raised concerns about their reliability beyond English.
Approach:	They propose a benchmark for cross-lingual sense disambiguation that uses false friends to identify the limitation of cross-linguistic sense disembarrassment in LLMs.
Outcome:	The proposed benchmark pinpoints the limitation of cross-lingual sense disambiguation in LLMs by using false friends in four languages.

A Checkpoint on Multilingual Misogyny Identification (2022.acl-srw)

Copied to clipboard

Arianna Muti, Alberto Barrón-Cedeño

Language Models

Challenge:	a study on hate speech against minorities in Italian tweets found that 1 women are the most targeted group.
Approach:	They propose to train monolingual transformers and multilingual transformer models with monolingual data in English, Italian, and Spanish to detect misogyny in tweets.
Outcome:	The proposed model achieves state-of-the-art on English, Italian, and Spanish.

A Unified Generative Framework for Bilingual Euphemism Detection and Identification (2024.findings-acl)

Copied to clipboard

Yuxue Hu, Junsong Li, Tongguan Wang, Dongyu Su, Guixin Su, Ying Sha

Multilinguality

Challenge:	Existing euphemism datasets are only domain-specific or language-specific.
Approach:	They propose a unified model to jointly conduct bilingual euphemism detection and identification tasks.
Outcome:	The proposed model is effective and provides a new reference standard for euphemism detection and identification.

PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification (D19-1)

Copied to clipboard

Yinfei Yang, Yuan Zhang, Chris Tar, Jason Baldridge

Multilinguality

Challenge:	Existing work on adversarial data generation focuses on English . Existing multilingual datasets show effectiveness of deep, multilingual pre-training .
Approach:	They propose a dataset of 23,659 human translated PAWS evaluation pairs in six languages . they show the effectiveness of deep, multilingual pre-training while leaving considerable headroom .
Outcome:	The proposed model shows that multilingual training and evaluation regimes are more accurate than previous models.

Wiki-40B: Multilingual Language Model Dataset (2020.lrec-1)

Copied to clipboard

Mandy Guo, Zihang Dai, Denny Vrandečić, Rami Al-Rfou

Language Models

Challenge:	We propose a new multilingual language model benchmark that is composed of 40+ languages spanning several scripts and linguistic families.
Approach:	They propose a multilingual language model benchmark composed of 40+ languages . they train monolingual causal language models using a state-of-the-art model .
Outcome:	The proposed model is composed of 40+ languages spanning several scripts and linguistic families.

Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference (2021.findings-acl)

Copied to clipboard

Hai Hu, He Zhou, Zuoyu Tian, Yiwen Zhang, Yina Patterson, Yanting Li, Yixin Nie, Kyle Richardson

Multilinguality

Challenge:	Multilingual transformers have been shown to have remarkable transfer skills in zero-shot settings.
Approach:	They investigate cross-lingual transfer abilities of XLM-R for Chinese and English natural language inference using a large scale Chinese dataset.
Outcome:	The proposed model trains on Chinese and English natural language inference datasets.

VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation (2021.acl-long)

Copied to clipboard

Fuli Luo, Wei Wang, Jiahao Liu, Yijia Liu, Bin Bi, Songfang Huang, Fei Huang, Luo Si

Language Models

Challenge:	Existing work in multilingual pretraining relies on the shared vocabulary and bilingual contexts to encourage the correlation across languages.
Approach:	They propose to plug a cross-attention module into a Transformer encoder to explicitly build the interdependence between languages.
Outcome:	The proposed model outperforms existing models on XTREME and English-to-French translation datasets.

Multilingual Word Segmentation: Training Many Language-Specific Tokenizers Smoothly Thanks to the Universal Dependencies Corpus (L18-1)

Copied to clipboard

Erwan Moreau, Carl Vogel

Syntactic Text Processing

Challenge:	Towards language scalability, major progress has been achieved in multilingual language technology in recent years.
Approach:	They propose a tokenizer that can be trained from any Universal Dependencies corpus dataset . they argue that tokenization should be seen as a supervised task and scalability requires a software engineering process across languages.
Outcome:	The proposed tokenizer can be trained from any dataset in the corpus UD2 . the proposed software tool relies on elephant to perform the training .

Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models (2021.findings-acl)

Copied to clipboard

Laura Pérez-Mayos, Alba Táboas García, Simon Mille, Leo Wanner

Syntactic Text Processing

Challenge:	Multilingual Transformer-based language models have been shown to be excellent learners in crosslingual transfer tasks.
Approach:	They evaluate the syntactic generalization capabilities of BERT and RoBERTa models on English and Spanish tests.
Outcome:	The proposed models perform well on English and Spanish tests, and the proposed tests are compared against models on the same language and models on two different languages.