跨语言迁移可能会加剧情感分析中的偏见
Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
AI总结：
本研究通过反事实评估发现，情感分析中使用跨语言迁移通常比单语迁移引入更多性别和种族偏见，并发布了1,525个模型及评估代码以促进相关研究。
摘要：
情感分析（SA）系统被广泛部署于世界上多种语言中，且有充分证据表明这些系统存在人口统计学偏见。在英语以外的语言中，通常使用基于预训练模型（包括在其他语言上训练的多语言模型）的迁移学习来补充稀缺的训练数据。在某些情况下，甚至监督数据也来自其他语言。跨语言迁移是否也会引入新的偏见？为了回答这个问题，我们使用反事实评估来测试，与单语迁移设置相比，使用跨语言迁移时是否会引入性别或种族偏见。在五种语言中，我们发现使用跨语言迁移的系统通常比其单语对应系统更具偏见。我们还发现种族偏见比性别偏见更为普遍。为了促进该主题的进一步研究，我们发布了本研究中使用的情感模型以及训练过程中的中间检查点，共计1,525个不同的模型；我们还发布了我们的评估代码。
英文摘要：
Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and there is well-documented evidence of demographic bias in these systems. In languages beyond English, scarcer training data is often supplemented with transfer learning using pre-trained models, including multilingual models trained on other languages. In some cases, even supervision data comes from other languages. Does cross-lingual transfer also import new biases? To answer this question, we use counterfactual evaluation to test whether gender or racial biases are imported when using cross-lingual transfer, compared to a monolingual transfer setting. Across five languages, we find that systems using cross-lingual transfer usually become more biased than their monolingual counterparts. We also find racial biases to be much more prevalent than gender biases. To spur further research on this topic, we release the sentiment models we used for this study, and the intermediate checkpoints throughout training, yielding 1,525 distinct models; we also release our evaluation code.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
