paper-with-me

Papers

Can Existing Methods Debias Languages Other than English? First Attempt to Analyze and Mitigate Japanese Word Embeddings

2020-12-01 · GeBNLP (COLING) 2020 12 · Masashi Takeshita, Yuki Katsumata, Rafal Rzepka, Kenji Araki

It is known that word embeddings exhibit biases inherited from the corpus, and those biases reflect social stereotypes. Recently, many studies have been conducted to analyze and mitigate biases in word embeddings. Unsupervised Bias Enumeration (UBE) (Swinger et al., 2019) is one of approach to analyze biases for English, and Hard Debias (Bolukbasi et al., 2016) is the common technique to mitigate gender bias. These methods focused on English, or, in smaller extent, on Indo-European languages. However, it is not clear whether these methods can be generalized to other languages. In this paper, we apply these analyzing and mitigating methods, UBE and Hard Debias, to Japanese word embeddings. Additionally, we examine whether these methods can be used for Japanese. We experimentally show that UBE and Hard Debias cannot be sufficiently adapted to Japanese embeddings.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

Debiasing Multilingual LLMs in Cross-lingual Latent Space

2025-08-25 · Qiwei Peng, Guimin Hu, Yekun Chai, Anders Søgaard arxiv

Debiasing techniques such as SentDebias aim to reduce bias in large language models (LLMs). Previous studies have evaluated their cross-lingual transferability by directly applying these methods to LLM representations, r…

Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models

2026-04-03 · Haoyu Liang, Peijian Zeng, Wentao Huang, Aimin Yang 외 arxiv

Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this…

parameter-efficient fine-tuningData Augmentation

From Measurement to Mitigation: Exploring the Transferability of Debiasing Approaches to Gender Bias in Maltese Language Models

2025-07-03 · Melanie Galea, Claudia Borg arxiv

The advancement of Large Language Models (LLMs) has transformed Natural Language Processing (NLP), enabling performance across diverse tasks with little task-specific training. However, LLMs remain susceptible to social …

Data Augmentation

Bias Beyond English: Evaluating Social Bias and Debiasing Methods in a Low-Resource Setting

2025-04-15 · Ej Zhou, Weiming Lu

Social bias in language models can potentially exacerbate social inequalities. Despite it having garnered wide attention, most research focuses on English data. In a low-resource scenario, the models often perform worse …

FairnessMultilingual NLP

Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques

2023-10-16 · Manon Reusens, Philipp Borchert, Margot Mieskes, Jochen De Weerdt 외

This paper investigates the transferability of debiasing techniques across different languages within multilingual models. We examine the applicability of these techniques in English, French, German, and Dutch. Using mul…

Cross-Lingual Transfer