Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification
Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation model to reduce the gender bias and improve performance of text classifiers under multilingual settings. We evaluate our approach on two text classification tasks, hate speech detection and rating prediction, and demonstrate the effectiveness of our approach with three fair-aware baselines.
Code (1)
Tasks
Domain AdaptationHate Speech DetectionMultilingual text classificationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models
Multilingual vision-language models promise universal image-text retrieval, yet their social biases remain under-explored. We present the first systematic audit of three public multilingual CLIP checkpoints -- M-CLIP, NL…
Image-text RetrievalText RetrievalMultilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
Text-to-image generation models have recently achieved astonishing results in image quality, flexibility, and text alignment, and are consequently employed in a fast-growing number of applications. Through improvements i…
Image GenerationMultilingual Text-to-Image GenerationPrompt EngineeringText to Image Generation+1Gender Lost In Translation: How Bridging The Gap Between Languages Affects Gender Bias in Zero-Shot Multilingual Translation
Neural machine translation (NMT) models often suffer from gender biases that harm users and society at large. In this work, we explore how bridging the gap between languages for which parallel data is not available affec…
Machine TranslationNMTTranslationColombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMs
One of the goals of fairness research in NLP is to measure and mitigate stereotypical biases that are propagated by NLP systems. However, such work tends to focus on single axes of bias (most often gender) and the Englis…
FairnessTarget-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation
Gender bias is a significant issue in machine translation, leading to ongoing research efforts in developing bias mitigation techniques. However, most works focus on debiasing bilingual models without much consideration …
Contrastive LearningMachine TranslationTranslation